review-tasks
Skill31 starsChanged 6 months agoMITView on GitHub
Reviews an implementation task plan against its approved proposal, specifications, design, and test plan, finding only defects that can be corrected in the task files; use when asked to review tasks, review an implementation plan, verify task and automated-test coverage, or check whether a task breakdown is ready for autonomous implementation.
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Read all definition and task artifacts before judging the plan.
- Distinctive: line 16
Check that the tasks:
- Distinctive: line 23
keep tests, ordinary documentation, setup, and refactoring with the behavior they support.
- Distinctive: line 27
Do not ask for new product, scope, architecture, or testing-strategy decisions.
- Distinctive: line 33
Every finding must be correctable only in the task index or detailed task files.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Review Tasks
Review whether the task index and detailed task files are a faithful, complete, executable translation of the approved proposal, specifications, design, and test plan.
Read all definition and task artifacts before judging the plan. Inspect relevant repository structure when needed to verify feasibility, paths, dependencies, test placement, or implementation boundaries. The definition artifacts are immutable inputs, not review targets.
Review focus
Check that the tasks:
- cover approved requirements, scenarios, design obligations, migration, deliverables, and assigned integration or E2E tests without adding scope;
- are self-contained for implementors with no hidden session context, including exact artifact citations, constraints, acceptance criteria, and done conditions;
- form meaningful, right-sized delivery units with workable dependencies and ordering;
- keep tests, ordinary documentation, setup, and refactoring with the behavior they support;
- identify relevant implementation surfaces without prescribing line-by-line code; and
- contain no duplicate, contradictory, orphaned, or unreachable work.
Do not ask for new product, scope, architecture, or testing-strategy decisions. If a concern requires changing an approved artifact, it is outside this review and must not become a task finding. Do not review implementation correctness or modify files.
Report
Every finding must be correctable only in the task index or detailed task files. Cite the exact task section and controlling artifact section, explain the implementation risk, and recommend the specific task edit. Rank findings by impact and end with a readiness assessment; say explicitly when no actionable task defect remains.
## Findings
### [high|medium|low] <title>
- Task: <task file and section>
- Controlling artifact: <artifact and section>
- Risk: <implementation consequence>
- Correction: <specific task edit>
## Readiness Assessment
<Whether the task plan is ready and why.>Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- nesnilnehc/ai-cortex★ 8same name
- ir0nfelix/study_materials★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- releaseSkill
- releaseSkill
- ask-questionsSkill
- call-agentSkill
- designSkill
- finalize-prSkill
- fix-prSkill
- handoffSkill
- implement-changeSkill
- initSkill
- orchestrate-changeSkill
- plan-tasksSkill
- prepare-acceptanceSkill
- proposal-reviewSkill
- proposeSkill
- push-prSkill
- review-approachSkill
- review-assumptionsSkill
- review-specSkill
- session-reportSkill
- simple-planSkill
- specSkill
- task-complianceSkill
- test-flowsSkill
- test-planSkill
- verify-behaviorSkill
- wait-ciSkill
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.

