Give someone an answer in the conversation that they can read in two minutes before committing time to an idea: which other efforts in the organisation already do, or did, something like it, who owns each one, how close each is, and what to do about it. It’s for the person about to start, so they can talk to the right people first, join work that’s already moving, draw a line between their work and someone else’s, or reuse what was built.
Nothing in Projects, Jira or Confluence links an effort to the other efforts like it. Two teams can build the same thing under different names for months, and a project cancelled last quarter leaves no trace in the next team’s plan. The value of this skill is the judgement a project directory or a search results page can’t make: it finds efforts named differently from the idea, reads what each one actually does rather than what it’s called, sorts them into a fixed set of overlap classes, and turns each into one move with an owner to contact.
Load the teamwork-graph-context skill first and follow it for gathering context, labelling sources, keeping sensitive content out and optional publishing. Its “Searching” and “Sensitive content” sections matter most here. This file adds what’s specific to finding similar efforts.
This skill selects “Answer-first delivery” in teamwork-graph-context: gather and assess, answer in the conversation, then ask whether the user wants an HTML report. Do not write report data, run a renderer or create an artifact unless the user requests an export, HTML report or publication. Use the existing report layout only for that optional export. Offer Atlassian Artifacts publication only after confirming availability; exporting does not authorise publishing.
atlassianUserInfo once, only to recognise the user’s own work. Make no manager or reporting-line lookups: don’t call getPeopleInfo with manager or directReports, and don’t use getWorkPortfolio or getCollaborators, which describe people rather than an idea.teamwork-graph-context), say so before building: efforts can only come from docs and chat, and owners from authors.teamwork-graph-context describes: Slack or Teams, to read a public channel thread when an effort’s only owner signal is a snippet. GitHub, to read a repository’s README or pull request author when the graph returns it empty (raw: {}). Never read direct or group messages through them.Unless the user asks for a deeper pass, stay within these, and say in the footer if one was reached:
| Tool | Cap | Where |
|---|---|---|
searchProjects (through discover and executeRead) |
4 | 2 in Step 2, 2 in Step 4 |
search |
6 | 4 in Step 2, 2 in Step 4 |
JQL (searchJiraIssuesUsingJql) |
2 | 1 in Step 2, 1 in Step 5 |
getGraphContext |
4 | Step 5, one full call per top effort |
| Product reads | 8 calls | Step 5: getProject, getConfluenceContent, getLoomVideo, a code or README read, and getGraphObject (one batched call counts as one) |
getPeopleInfo |
2 | Step 6, batches of up to 10 account IDs |
listArtifacts |
1 | Step 1, the user’s own Artifacts |
search, getGraphContext and getPeopleInfo use Rovo credits. A typical run makes 22 to 30 calls, including one discover for each operation reached through executeRead.
Calls in the same step that don’t depend on each other go out together, as “Fetch in parallel” in teamwork-graph-context describes: the whole sweep in Step 2, the echo pass in Step 4, and the reads in Step 5. Send at most 4 getProject calls at once: on real data a read straight after a batch of 7 returned 429.
getAccessibleAtlassianResources once for the cloudId and the site’s products list, and atlassianUserInfo once for the user’s account ID. If artifacts is in the products list, run listArtifacts (through discover and executeRead) with limit: 100, and keep the IDs and titles: search returns an Artifact’s author as a third-party identity, not an account ID, so this is the only way to recognise the user’s own.getConfluenceContent (content_format: markdown, detail: full), getProject with include: ["description"], or getJiraIssue. Use it to frame the idea and take the terms from it; supplying a record doesn’t establish that the user owns it. Keep that record as the idea’s anchor rather than a separate result. Assess its linked records individually in Step 3. This initial read doesn’t count towards the product-read budget.Send all of these together, at most 2 searchProjects, 4 search and 1 JQL:
searchProjects x2 (through discover and executeRead), with query set to the core name and then the user’s own name (or, if they gave none, the actor synonym), and limit: 20. It matches the words of project names closely, and plurals and longer phrases often miss: on real data “daily brief” found 7 projects, “morning brief” found none, and “video overlay” missed two projects named “Overlays”. Don’t filter by status: done, paused and cancelled projects are part of the answer.search (STANDARD, targetApp: ALL, limit: 20) x2, with the user’s own name (or the core name) and the “what it does” phrase. search finds project records that searchProjects misses: a hit whose URL is a project (/project/) counts as a project record, the same as one from searchProjects.search (STANDARD, targetApp: THIRD_PARTY, limit: 20) with the actor synonym.search (STANDARD, targetApp: CONFLUENCE, limit: 20) with the core name plus “plan” or “design” (“daily brief design”).issuetype = Epic AND (summary ~ "\"<core name>\"" OR summary ~ "\"<synonym 1>\"" OR summary ~ "\"<synonym 2>\"") ORDER BY updated DESC, with fields: ["summary", "status", "project", "assignee", "resolution", "resolutiondate"] and maxResults: 20. Without the epic filter, it returns pages of unrelated tasks that share a word.If search warns that some sources couldn’t be queried, say so in the footer.
Work through every hit in this order.
teamwork-graph-context says, before reading anything else about them. This idea search reaches far, and on real data every sweep surfaced some. Leave out, without listing, counting in the card or describing them:
/archives/D, a channel starting mpdm-)Efforts are often named differently from the idea, so a search with the idea’s words finds a doc or a chat message about an effort but misses its record. An echo search reuses the effort’s own vocabulary. On real data, this is what found the project record, owner and team of the hardest overlap, and the real names of efforts that the first sweep’s generic words missed.
searchProjects with the effort’s own distinctive word plus its short form if it has one (“SM checker” for “Search migration checker”), as it appears in its title or snippet. If that’s a term the sweep already searched, use another name the effort goes by, or spend the call on a search with targetApp: CONFLUENCE and the effort’s name insteadsearch (STANDARD, targetApp: ALL, limit: 20) with the effort’s own name plus one distinctive word from its snippetRank the candidates as Assess describes, using what you have so far, and read the top 4, or fewer if fewer could overlap. Send the reads together.
getProject with identifier set to the ARI or key, include: ["description", "updates", "teams", "contributors", "goals", "links", "dependencies"] and limits: {updates: 3, teams: 5, contributors: 10, goals: 5, links: 10, dependencies: 10}. The owner, status, phase, teams, goal, and the latest user update. When the description is only a URL to a page or doc, read that page as the description: it counts as one product read.key in (...), with fields: ["summary", "description", "status", "assignee", "reporter", "resolution", "resolutiondate", "issuelinks"]. Read descriptions only for these.getConfluenceContent with content_format: markdown and detail: full, for an effort whose only record is a page. Use the body to say what it does, and take its status line and its named owners from it.getLoomVideo without the transcript, for its title, description and owner. Read the transcript only when the description doesn’t say what was built, and apply “Sensitive content” to it.getTeam), shown as “Owned by [team]”, and its state as its status. Use the description and links to say what it does.teamwork-graph-context describes (finding and reading a CODEOWNERS, manifest or README counts as one product read; brace globs in a path return a 400). Read a README to say what it does. A page that documents a repository clusters with it: its writer is “Wrote”, and the owner comes from the repository.getGraphObject, batched. For a GitHub object that returns raw: {}, use the vendor connector or keep the snippet.detailLevel: full and relationshipTypes for its type:
atlassian_user_owns_atlassian_project, atlassian_user_contributes_to_atlassian_project, atlassian_project_contributes_to_atlassian_goal, atlassian_project_links_atlassian_project, jira_work_item_tracks_atlassian_project. Atlas keys don’t resolve here, so pass the project’s ARI.atlassian_user_owns_confluence_page, atlassian_user_created_confluence_page, atlassian_user_contributed_to_confluence_pageupdateType: on real data a bot’s cancellation update was marked USER. Read the creator’s name and the text instead.Stop gathering when each of the top 4 has an owner and a status, and you can say what it does from its own records. One extra read is fine if it could change the top effort’s class.
getPeopleInfo with up to 10 account IDs per call, at most 2 calls: the owner of each effort, up to 2 contributors each, and the people who posted each project’s latest updates, so an inactive owner’s fallback needs no second call. No manager or directReports. Use only the name. It returns no team: take the team from the project’s teams, and otherwise show none. Ignore job title, department, email and location, and never show them.CODEOWNERS): show “Owner not recorded”, and give the channel or page to ask in, if there is one.An effort overlaps the idea only when its own records say so, as Step 5 defines them: a project description or update, an epic description, a page or doc body, a README, a Loom description, or a search snippet of that body. Never infer an overlap from a title match alone. Compare what it does with the facets from Step 1 that aren’t blank:
Count a full match as 1 and a match in part as a half, for ranking. Write down the main difference in one phrase (“runs once a week, not on every change”, “for support leads, not every user”), or “none found”. The card shows it.
A candidate whose description you couldn’t read, or that matches only on its title, goes in “Names that matched, not checked” (up to 3), with its record’s status and no class.
Show the record’s own status beside the class, in plain text (“Projects · Paused”).
One per effort. Decide in this order, and take the first that fits:
| Class | When | Lozenge |
|---|---|---|
| Cancelled | The record’s status is Cancelled, or a Jira resolution of Won’t Do, Declined or Duplicate, and the outcome matches fully or in part | neutral |
| Done before | The record is Done, Completed or Resolved as Done, or a page or update says it shipped, and the outcome matches fully or in part, and nothing in the same line of work is still active | success |
| Same | The outcome matches fully, every other facet the user gave matches fully, and its records name no different audience. It may be active, paused or inactive | warning |
| Partial overlap | The outcome matches in part, or fully with a different audience, scope or delivery, or it covers part of the idea | information |
| Adjacent | The outcome differs, but the mechanism or the audience matches, so it could share parts or users | discovery |
Anything that matches none of these isn’t an effort to know about: drop it.
Cancelled is not failed. Read who cancelled it:
Rank the efforts checked in Step 5 by how closely each matches the idea. Only those checked efforts are eligible for the main results:
Don’t rank by an effort’s size, its team, its owner’s seniority, its project status colour or how many hits it got. Show at most 4 efforts. If any checked effort is In progress, the closest one is among them. Otherwise, if any checked effort is active, at least one active effort is. If more qualify, say “and N more” in the footer with their names as plain text.
One move per effort, with a one-line reason that cites its evidence:
| Class | Move | Unless |
|---|---|---|
| Same, active, with an owner | Join: the work is already moving, so offer to contribute rather than start a second one | It’s Pending, Paused, inactive or has no owner: then Talk |
| Partial overlap | Differentiate: agree with the owner where one effort ends and the other starts, using the main difference | It covers most of the idea’s outcome, for the same audience, and is in progress: then Join. It’s inactive and its plan or design is written up: then Reuse |
| Done before | Reuse: use what was built, or what was learned, before building again | Nothing reusable is linked or recorded (no repo, page, demo, or an update recording a launch or GA): then Talk |
| Cancelled | Talk: ask the owner what happened before repeating it | |
| Adjacent | Reuse when it has a shipped part the idea could use | Otherwise Talk |
With no owner, the move stays, and the reason names the channel or page to go through. The moves are suggestions. Write each reason from the records (“Same outcome and audience, in progress, update 3 days ago”), never from a guess about the people.
None. The card suggests a move and a first message, but the user acts on it. Don’t message, follow, join, link, comment or create anything for the user.
Ask whether the user wants this exported to an HTML report. If they have already explicitly requested an export, HTML report or publication, proceed with that requested build without asking again. Otherwise stop here until they answer; a normal invocation of this skill does not request a report. Follow the shared availability and confirmation checks before offering or performing publication.
Only after the user requests the report, write its data as one JSON file and run the renderer in this folder:
python3 <this skill's folder>/render.py card.json before-you-start-<idea>.html
example.json in this folder (made-up sample data). Copy its keys and fill them from the steps above. Text fields, links, lozenges and icons follow the shared rules in the atlassian-design skill’s references/data-format.md. Leave out a key you have nothing for.headline is the h1 (“3 efforts to know about”), verdict the verdict lozenge and idea the idea restated in one sentence. Each of efforts, ranked, is {"link", "class", "status", "does", "facets", "owner", "contributors", "move", "linked", "found", "earlier", "next", "note", "connected"}: class the class lozenge, status the record’s status line (“Projects · On track”), does the line on what it does, facets the matched facets and main difference, owner {"name", "label", "team"} labelled as Step 6 says (just {"label"} for “Owner not available” or “Owner not recorded”), contributors up to 2 names, move {"label", "why"}, linked up to 4 links and found up to 3, earlier and next the other phases, note the line for a bot-cancelled effort, and connected “You’re already connected” when Step 3 or Step 5 found it. message is the suggested first message, left out for “Nothing close found”. unchecked lists the names that matched as {"link"}.references/hand-built.md in this folder.The rules below say what the renderer builds, and what each part of the data must hold.
h1 (“3 efforts to know about”), the verdict lozenge on the right, and the idea restated in one sentence under it in subtle text. Then, in small subtlest text: “Based on what each effort’s own records say it does. The moves are suggestions.”project): one row per effort, ranked. Each row:
comment): one message about the top effort, to its Owner, or else the person who created it or wrote it, or else its channel, naming the effort and the user’s idea (“I’m about to start a daily summary for support leads. I saw Morning digest in Projects. Could we compare scope before I begin?”), in a quote block with a “Copy” button. Labelled “Suggested”. When the user is already connected, write it as a follow-up between colleagues, not an introduction. Leave it out for “Nothing close found”.search), only if any: one line each, a smart link and its status, with “Title matches only. We couldn’t read what it does.”teamwork-graph-context describes: the apps searched, the terms searched (including echo searches), how many candidates were considered and how many efforts were shown, “N of your own items were left out”, “Some results weren’t used” when Step 3.1 dropped anything, whether the echo pass ran, any budget cap reached, and gaps such as owners from chat only or GitHub authors not available.Static only. Finding efforts depends on open-ended search and on the sensitive-content judgement, which page code can’t make. To refresh, run the skill again.
teamwork-graph-context, and publish only if requested. Exporting the report does not authorise publication.