kanban-card-review
Skill6 starsChanged 3 months agoMITView on GitHub
Read-only review of a card lifecycle or a proposed promotion against history, dependencies and evidence, returning APPROVE or REQUEST CHANGES. Use for independent review of card stage changes. RU: ревью карточки, проверка перехода.
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/agent-hook-verify/references/claude.mdCLAUDE.md
- agent-command-runSkill
- agent-context-auditSkill
- agent-hook-verifySkill
- agent-integration-auditSkill
- agent-model-findSkill
- agent-project-syncSkill
- agent-skill-findSkill
- agent-skill-syncSkill
- agent-terms-defineSkill
- agent-workspace-migrateSkill
- api-contract-defineSkill
- api-docs-syncSkill
- api-stream-diagnoseSkill
- api-yandex-oauth-runSkill
- code-async-reviewSkill
- code-cli-buildSkill
- code-config-auditSkill
- code-durable-reviewSkill
- code-performance-fixSkill
- code-state-verifySkill
- deploy-artifact-publishSkill
- deploy-rollout-runSkill
- design-brand-buildSkill
- docs-claims-verifySkill
- docs-diagram-buildSkill
- docs-prose-fixSkill
- git-branch-cleanSkill
- git-merge-syncSkill
- git-path-runSkill
- git-repo-runSkill
- git-worktree-guardSkill
- infra-container-setupSkill
- infra-network-diagnoseSkill
- infra-project-migrateSkill
- infra-runbook-buildSkill
- kanban-board-auditSkill
- kanban-card-buildSkill
- kanban-card-planSkill
- kanban-card-runSkill
- kanban-card-verifySkill
- kanban-epic-coordinateSkill
- kanban-queue-coordinateSkill
- kanban-roadmap-planSkill
- kanban-schedule-runSkill
- monitor-telemetry-setupSkill
- personal-action-planSkill
- quality-artifact-verifySkill
- quality-change-reviewSkill
- quality-change-verifySkill
- research-prior-art-findSkill
- research-source-auditSkill
- research-source-findSkill
- research-spike-runSkill
- security-access-diagnoseSkill
- security-api-hardenSkill
- security-boundary-hardenSkill
- security-boundary-reviewSkill
- security-filesystem-hardenSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read-only review of a card lifecycle, status document or proposed promotion.
- Distinctive: line 12
Use for read-only review of a card's lifecycle or a status document that cites it.
- Distinctive: line 14
Verify one canonical card and ID, its actual stage, any maintained status field, dependencies, acceptance criteria, and referenced cards.
- Very specific: line 16
Keep ready or a pilot handoff distinct from done, production rollout, rollback, and any other acceptance gates.
- Distinctive: line 17
Run the available read-only board and diff checks.
- Distinctive: line 24
Use for a read-only verdict on an already proposed or performed lifecycle promotion.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Kanban card review
Read-only review of a card lifecycle, status document or proposed promotion. Do not edit, commit or publish during the review.
Lifecycle review
Use for read-only review of a card's lifecycle or a status document that cites it. Capture the current source, branch, base, HEAD, affected paths, and repository status when applicable. Inspect the complete baseline-to-HEAD change, not only the last repair.
- Verify one canonical card and ID, its actual stage, any maintained status field, dependencies, acceptance criteria, and referenced cards. Do not infer completion from a directory name alone.
- Read the complete current card and its decisions and execution log. Identify active wording that contradicts later decisions, such as an unresolved promotion question or an obsolete instruction to remain in an earlier stage. Recommend marking superseded statements as historical with the resolving evidence, or removing redundant wording when authorized; retain unresolved future gates.
- Keep
readyor a pilot handoff distinct fromdone, production rollout, rollback, and any other acceptance gates. Check that roadmap and status claims describe the actual verified endpoint rather than elevating it. - Run the available read-only board and diff checks; distinguish current results from historical claims and report unavailable checks. A clean linter alone does not prove lifecycle consistency.
- Repeat the relevant final snapshot before the verdict. Classify findings by impact: a false completion or dependency claim that could bypass a security or production gate is high; conflicting path, status, or card text that can misdirect work is medium; stale wording with no active scheduling effect is low. Report each finding with its exact source, contradictory claim, current evidence, impact, and minimum correction. Do not edit, commit, or publish during a read-only review.
See historical lifecycle wording for the targeted review and evidence checklist.
Promotion review
Use for a read-only verdict on an already proposed or performed lifecycle promotion.
Freeze branch, HEAD, review baseline, untracked files, changed-file summary and diff check; review the complete current card and its change rather than only a later correction. Check the actual stage and any maintained status field, uniqueness, approved scope and exclusions, dependencies, safety boundaries, and required verification claims. Compare current facts to the authoritative sources and related cards; recompute applicable catalog rows, targets and special variants instead of relying on examples, and keep explicitly deferred work separate. Verify any relevant execution identity, resource isolation and security prerequisites remain distinct from output classification.
Inspect the entire card for unresolved questions, unqualified stale decisions, and contradictions. Re-run safe authorized targeted and whole-board lint, diff and relevant static parsing; distinguish current from carried results, and report unavailable checks. A clean linter alone is not proof that scope or acceptance is correct. Repeat the status snapshot before the verdict.
Return evidence-backed APPROVE or REQUEST CHANGES, with the exact location, contradictory claim, source evidence, impact, and smallest correction for each finding. A confirmed blocking contradiction prevents approval. Do not edit, commit, or publish during this review.
See the promotion checklist for review evidence and safety boundaries.
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.

