review-task
Skill0 starsChanged 41 days agoMITView on GitHub
Review an existing docs/wip implementation against its frozen contract and current snapshot. Use for a requested task review; do not repeat unchanged reviews or edit implementation code.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- qivora-labs/agentinittheir own version, first seen Nov 15, 2026
- ModelEngine-Group/fit-frameworktheir own version, first seen Oct 8, 2026
- harbor-framework/terminal-bench-sciencetheir own version, first seen Oct 8, 2026
- zahardev/aicontexttheir own version, first seen Apr 22, 2026
- adolfoaranaes12/BMAD-ENHANCEDtheir own version, first seen Jan 28, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- ModelEngine-Group/fit-framework★ 2.1ksame name
- harbor-framework/terminal-bench-science★ 854same name
- adolfoaranaes12/BMAD-ENHANCED★ 2same name
- zahardev/aicontext★ 2same name
- qivora-labs/agentinit★ 1same 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 repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- complete-taskSkill
- create-taskSkill
- start-taskSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
1
Distinctive
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
- Very specific: line 11
Read and follow the complete algorithm in docs/workflows/task-lifecycle.md, section /review-task Equivalent …
- Distinctive: line 14
Never rewrite working code and never emit a new full version of a file.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review Task
Review the active task using its contract and current implementation snapshot.
- Resolve this
SKILL.mdpath, including symlinks, to locate its owning workspace withAGENTS.mdanddocs/workflows/task-lifecycle.md. If these are absent, report missing workspace setup. - Read and follow the complete algorithm in
docs/workflows/task-lifecycle.md, section/review-taskEquivalent (docs/workflows/task-lifecycle.md#review-task-equivalent), and the policy it points to indocs/product/architecture/verification-contract.md→ Review policy. Resolve these paths from the workspace root. The linked procedure and policy own lifecycle details. - Decide whether to intervene at all as a separate first step, before deciding what to change.
- Judge only against the frozen contract. Taste, hypothetical future needs, and claims without reproducible scenario, test, or tool evidence are not defects.
- Never rewrite working code and never emit a new full version of a file. Propose the minimal fix for admissible findings only.
Reuse an unchanged recorded review. Report the blocking outcome, any non-blocking findings, and snapshot evidence as the linked procedure requires; do not edit implementation code during standalone review.
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.

