coven-task-manager
Skill75 starsChanged 4 months agoMITView on GitHub
Keep Coven task boards fresh by auditing stale, blocked, active, review, and completed work; use for scheduled task hygiene, task triage, and dynamic task-management runs.
In this repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/heygen-skills/CLAUDE.mdCLAUDE.md
- 1passwordSkill
- ask-curlSkill
- boardSkill
- cleanup-unused-filesSkill
- codeflow-maintainerSkill
- codex-session-managerSkill
- coven-astraSkill
- coven-board-entrySkill
- coven-charmSkill
- coven-cloud-maintainerSkill
- coven-codySkill
- coven-echoSkill
- coven-identity-canonSkill
- coven-kittySkill
- coven-parallel-workSkill
- coven-sageSkill
- daily-dev-agenticSkill
- discrawlSkill
- disk-space-optimizerSkill
- epubSkill
- familiar-board-stewardshipSkill
- heygen-avatarSkill
- heygen-videoSkill
- heygen-skillsSkill
- higgsfield-generateSkill
- higgsfieldSkill
- linear-issue-managementSkill
- lit-ui-designerSkill
- lobsterSkill
- maintainer-barSkill
- memory-recallSkill
- memory-timeline-managerSkill
- ml-engineerSkill
- nodriverSkill
- ocrSkill
- openclaw-devSkill
- openclaw-trustSkill
- opencoven-designSkill
- OpenCoven Role Creation ProcessSkill
- pr-agentSkill
- project-managerSkill
- prompt-engineerSkill
- prompt-vaultSkill
- research-ingestionSkill
- ritual-dapp-frontendSkill
- rollcallSkill
- security-agentSkill
- skill-scannerSkill
- slidev-deck-pipelineSkill
- tauri-apple-releaseSkill
- threejs-animationSkill
- tinyfish-agent-runSkill
- tinyfish-browserSkill
- tinyfish-fetchSkill
- tinyfish-searchSkill
- tinyfishSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 13 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈13
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill when asked to manage, refresh, audit, triage, or summarize Coven tasks, or when a scheduled automation asks for task-board …
- Distinctive: line 12
Start with the Cave task board from the skill directory:
- Distinctive: line 20
If the canonical repo path is different, run the helper from this skill directory:
- Very specific: line 30
Read Thread Coordination before touching individual cards.
- Distinctive: line 33
If multiple cards share a session, resume that session once and update all linked cards from the same evidence.
- Distinctive: line 34
If one familiar has multiple active lanes, choose the primary lane and mark the rest as waiting, review, or blocked with a reason.
- Distinctive: line 35
If multiple lanes touch the same repo or branch, verify branch/worktree ownership before allowing parallel writes.
- Distinctive: line 36
Prefer resuming a viable linked session over starting a new thread.
- Distinctive: line 38
Keep task state fresh:
- Distinctive: line 40
Keep blocked tasks explicit: include the blocker, owner, and smallest next unblock action.
- Distinctive: line 43
Update the freshness report after meaningful changes.
- Distinctive: line 47
Do not delete, archive, or bulk-close tasks unless the user explicitly asks.
- Distinctive: line 48
Do not invent blockers or progress.
- Distinctive: line 49
Do not mark a task done from memory alone.
- Distinctive: line 51
If evidence is missing, leave the task in place and write the missing check as the next action.
- Very specific: line 52
Do not spawn parallel work for the same repo/branch/session just because several cards look stale.
- Very specific: line 68
Use --status ACTIVE only when the user wants the automations enabled immediately.
≈ “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
Coven Task Manager
Use this skill when asked to manage, refresh, audit, triage, or summarize Coven tasks, or when a scheduled automation asks for task-board freshness.
Sources
Start with the Cave task board from the skill directory:
node ./task-manager.mjs reportThe helper reads ~/.coven/cave-board.json and writes ~/.coven/task-manager/freshness-report.md by default.
If the canonical repo path is different, run the helper from this skill directory:
node ./task-manager.mjs report --coven-home ~/.covenWorkflow
- Load the task board and build a freshness report.
- Inspect the report sections in this order:
Stale Running,Needs Human,Ready For Review, thenNext Actions. - Read
Thread Coordinationbefore touching individual cards. Treat it as the concurrency control surface for simultaneous sessions. - For every active/review/blocked thread, build a small ledger: card id/title, familiar, session id, repo/branch/worktree if known, last evidence checked, current state, and one next action.
- Resolve collisions before dispatching new work:
- If multiple cards share a session, resume that session once and update all linked cards from the same evidence.
- If one familiar has multiple active lanes, choose the primary lane and mark the rest as waiting, review, or blocked with a reason.
- If multiple lanes touch the same repo or branch, verify branch/worktree ownership before allowing parallel writes.
- Prefer resuming a viable linked session over starting a new thread; start a fresh thread only when no current session can be resumed.
- For each task that needs action, gather concrete evidence before changing state: linked sessions, git branches, PRs, CI, user messages, or task notes.
- Keep task state fresh:
- Move stale running work only when evidence shows it is blocked, ready for review, done, or abandoned.
- Keep blocked tasks explicit: include the blocker, owner, and smallest next unblock action.
- Move review tasks only after the actual review/CI state is checked.
- Mark work done only when merge, delivery, or acceptance evidence exists.
- Update the freshness report after meaningful changes.
Guardrails
- Do not delete, archive, or bulk-close tasks unless the user explicitly asks.
- Do not invent blockers or progress.
- Do not mark a task done from memory alone; verify current state first.
- Preserve user-written task notes. Append concise evidence instead of replacing useful context.
- If evidence is missing, leave the task in place and write the missing check as the next action.
- Do not spawn parallel work for the same repo/branch/session just because several cards look stale; reconcile the existing thread ledger first.
Default Automations
Install the default Codex automation set with:
node ./task-manager.mjs install-default-automations --status PAUSEDThe templates are:
coven-task-freshness-daily— daily sweep of stale, blocked, review, and active work.coven-task-blocked-escalation— weekday blocked-task escalation.coven-task-weekly-cleanup— weekly summary and cleanup recommendations.
Use --status ACTIVE only when the user wants the automations enabled immediately.
Local Market Install
To make the skill visible to the local Cave Skills market, symlink it into Coven home:
node ./task-manager.mjs install-local --status PAUSEDThe Cave market reads ~/.coven/skills/*/metadata.json through the Coven daemon.
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.

