release-research
Skill445 starsChanged 10 days agoMITView on GitHub
Investigate an eligible product release against source diffs and current docs. Read-only. Returns a feature list with evidence; does not open tickets or PRs.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/docs-style.mdcCursor rule
- add-docs-pageSkill
- docs-code-samplesSkill
- docs-editSkill
- docs-restructureSkill
- docs-reviewSkill
- docs-team-voiceSkill
- docs-tooling-notionSkill
- submit-integrationSkill
- update-integrations-prsSkill
- verify-against-sourceSkill
- deepagents-codeSkill
- deepagentsjsSkill
- deepagentsSkill
- openwikiSkill
- ship-docs-updateSkill
- langgraph-docsSkill
- write-timestampSkill
- pandas-patternsSkill
- deep-agentsSkill
- langchainSkill
- langgraphSkill
- langsmithSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 0 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill only inside the release-research subagent.
- Very specific: line 16
Call get_eligible_release for the product with defaults (min_age_days=7, max_age_days=30).
- Very specific: line 17
Read product memory (/memories/agent/<product>-releases.md) and skip features already tracked for that tag.
- Very specific: line 18
Call get_release_diff for the eligible tag (omit base_tag so it resolves the previous same-prefix release).
- Very specific: line 19
Call get_release_notes only as secondary context.
- Very specific: line 21
Call check_docs_coverage with the candidate symbols/flags and concrete docs page paths (for example src/oss/deepagents/customization.mdx).
- Very specific: line 22
Call get_docs_file on pages that might need updates when coverage is missing or wording looks wrong.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Release research (read-only)
Use this skill only inside the release-research subagent. You investigate. You do not ship.
Goal
For one product, decide which user-facing features in the eligible release need documentation updates, with citations from the product repo at that tag.
Steps
- Call
get_eligible_releasefor the product with defaults (min_age_days=7,max_age_days=30). Only releases in that window are in scope, including on a first run with empty memory. Stop if nothing is eligible. Prefer the newest candidate; do not walk older tags outside the window. - Read product memory (
/memories/agent/<product>-releases.md) and skip features already tracked for that tag. - Call
get_release_difffor the eligible tag (omitbase_tagso it resolves the previous same-prefix release). Treat the commit list and changed files as the primary signal. - Call
get_release_notesonly as secondary context. Notes are leads, not ground truth. - For each candidate feature from the diff, call
get_product_source_fileat the head tag and confirm the API, flag, command, default, or behavior exists. - Call
check_docs_coveragewith the candidate symbols/flags and concrete docs page paths (for examplesrc/oss/deepagents/customization.mdx). If every needle already appears and the existing wording is still correct, put the feature underskippedwith reason "already documented". - Call
get_docs_fileon pages that might need updates when coverage is missing or wording looks wrong. - Return a single research report. Do not call Linear or PR tools (you do not have them).
Research report format
Return JSON (as your final message text) with this shape:
{
"product": "deepagentsjs",
"head_tag": "deepagents@1.14.2",
"base_tag": "deepagents@1.14.1",
"features": [
{
"name": "FilesystemMiddleware offloadBinaryContent",
"needs_docs": true,
"reason": "New public option; docs Full stack and Override sections omit it.",
"docs_paths": ["src/oss/deepagents/customization.mdx"],
"evidence": {
"source_repo": "langchain-ai/deepagentsjs",
"source_tag": "deepagents@1.14.2",
"items": [
{
"path": "libs/deepagents/src/middleware/filesystem.ts",
"symbol": "offloadBinaryContent"
}
]
},
"diff_files": [
"libs/deepagents/src/middleware/filesystem.ts"
]
}
],
"skipped": [
{
"name": "internal test harness rename",
"reason": "No user-facing API or docs impact."
}
]
}Set needs_docs to false (or put the item under skipped) when source shows no user-facing change, when check_docs_coverage shows the symbols are already present and correct, or when docs already cover it.
Do not
- Open Linear issues or draft PRs
- Invent symbols that are not in
get_product_source_fileor the diff - Recommend docs for pure refactors, dependency bumps, or internal-only changes
- Bundle unrelated capabilities into one feature entry
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

