kb-review
Skill2 starsChanged 10 days agoMITView on GitHub
Work the Review-Queue and review_proposals items one by one (lint failure lists, cross-domain promotion candidates, overwrite-protection-rejected change proposals), giving analysis and fix suggestions; the final accept/reject is the user's. Use when the user says "work the review queue / look at the pending items / what's in the Review-Queue / walk me through the review backlog".
6 other projects use a version of this.
Adopted by
Most recently taken up by
- GeiserX/sstacktheir own version, first seen Nov 8, 2026
- timurgaleev/vibestacktheir own version, first seen Nov 8, 2026
- GeiserX/agent-skillstheir own version, first seen Nov 6, 2026
- GeiserX/claude-skillstheir own version, first seen Nov 6, 2026
- Movida/okf-hubtheir own version, first seen Aug 30, 2026
- lee-agi/agent-os-assettheir own version, first seen Aug 22, 2026
Used with
Projects with it also use docs-loop, full-loop and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GeiserXSkilldocs-loop
Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.
Also in 3 projects that use this
GeiserXSkillfull-loop
Drive a repository to done with sergio-loop, then keep improving it with refine-loop at a descending theta. Use only when the user explicitly invokes full-loop.
Also in 3 projects that use this
joris887Skillrefine-loop
Use when the user wants iterative self-improvement on a deliverable (document, implementation, prompt, design) until completion criteria are met.
Also in 3 projects that use this
RandyRawgustSkillrevive
Scan every project in 02 - Projects/ (and follow path: frontmatter to on-disk location), check git activity, surface dormant projects with one-page resurrection plans. Use when Andy says revive, resurrect, dormant projects, what projects could I pick back up, find stalled work.
Also in 3 projects that use this
tekumaraSkillfile-pr
Raise a concise pull request. Use when the user asks to raise, open, or create a PR.
Also in 3 projects that use this
- +7 more from GeiserX
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- timurgaleev/vibestack★ 8same name
- GeiserX/agent-skills★ 6same name
- GeiserX/sstack★ 6same name
- GeiserX/claude-skills★ 5same name
- lee-agi/agent-os-asset★ 1same name
- Movida/okf-hub★ 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 repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ingestSkill
- kb-postmortemSkill
- kb-qaSkill
- kb-querySkill
- kb-saveSkill
- pipeline-doctorSkill
- skill-evolveSkill
- source-preflightSkill
- source-xraySkill
- wiki-lint-semanticSkill
- ingestSkill
- kb-postmortemSkill
- kb-qaSkill
- kb-querySkill
- kb-reviewSkill
- kb-saveSkill
- pipeline-doctorSkill
- skill-evolveSkill
- source-preflightSkill
- source-xraySkill
- wiki-lint-semanticSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 5 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
After the user confirms, execute the matching fix/promotion/marking.
- Distinctive: line 41
If the user confirms a fix: the matching proposed page, the registry-derived rebuild, or a new proposal.
- Very specific: line 56
Run vault-changing commands (e.g.
- Very specific: line 57
After a fix is verified, retire the matching review_proposals rows with proposals-resolve (dry-run first, then --apply after user …
- Distinctive: line 65
Before preparation, declared citation-removal SHA values must be a subset of the current live page citations.
- Very specific: line 67
If the operation is committing, recover that operation before any ordinary lint.
- Distinctive: line 114
Every pending item has a class, a suggestion, and a user-decision state.
- Distinctive: line 115
No target vault page edited without user confirmation.
- Very specific: line 117
After a confirmed promotion, promote-concept + rebuild-registry were run.
- Very specific: line 118
After a lint-violation fix, the matching lint was re-run.
- Distinctive: line 121
No human page was auto-overwritten.
“Common” is measured: kept by at least 6 in 10 of the 6 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
kb-review — Review-Queue processing
Work wiki/Review-Queue/ and review_proposals items one by one. By default it only analyzes and
suggests; the final accept/reject is the user's. The execution layer is scripts/pipeline.py; this
skill only orchestrates, surfaces acceptance, and marks failure stops.
1. Triggers / Non-triggers
- Triggers: "work the review queue", "look at the pending items", "what's in the Review-Queue", "walk me through the review backlog", "handle the lint failures / cross-domain promotions / overwrite proposals".
- Non-triggers: ingesting a new source (use
ingest); read-only queries (usekb-query); saving a query result (usekb-save); a whole-vault semantic check (usewiki-lint-semantic); never accept a proposal or edit a human page without user confirmation.
2. Inputs
wiki/Review-Queue/*.md: lint failure lists,promotion-*.md,*-proposal.md, semantic-lint reports.- The machine ledger: the
review_proposalstable, viapython scripts/pipeline.py statusor related CLI state. - Relevant vault pages, the concept registry, source state.
3. Outputs
- For each item: a classification, the risk, a suggested fix, and whether a user decision is needed.
- After the user confirms, execute the matching fix/promotion/marking; without confirmation, do not edit the target.
For an
adopted/publishedlegacy page, prepare arevise-adoptedsidecar operation instead of fabricating an ingest workorder or editing live first. - Append
> handled: <conclusion>to a processed Review-Queue item, or note that it still awaits the user.
4. Dependencies
- CLI:
status,lint,revise-adopted,promote-concept,rebuild-registry; if needed, return toingestor the target source's lint loop. - Protocols:
docs/skill-runtime/schema.md,concept-resolution.md,save-back-policy.md. - Human-page protection stays top priority: a human page is edited by the user, never auto-overwritten by the skill.
5. Persisted artifacts
- The handled-markers on
wiki/Review-Queue/*.md. - If the user confirms a fix: the matching proposed page, the registry-derived rebuild, or a new proposal.
- The machine
review_proposalsstays the ledger; this skill does not hand-write the database.
6. CLI commands
python scripts/pipeline.py status
python scripts/pipeline.py revise-adopted --source <legacy_source> --request <revision-request.yaml>
python scripts/pipeline.py revise-adopted --source <legacy_source> --request <revision-request.yaml> --apply
python scripts/pipeline.py lint --source <source_id>
python scripts/pipeline.py promote-concept --id <canonical_id>
python scripts/pipeline.py rebuild-registry
python scripts/pipeline.py proposals-resolve --signature <kind> [--source <src>] --all-matching --applyRun vault-changing commands (e.g. promote-concept / page fixes / marking handled) only after user confirmation.
After a fix is verified, retire the matching review_proposals rows with proposals-resolve (dry-run
first, then --apply after user confirmation) so the skill-mine backlog stops counting fixed signals.
For adopted legacy pages, write authorization is not content attribution. The revision request must
name each target, reason, expiry, and structured HTTPS evidence; the credential freezes the current live
page. Edit only the generated candidate/files/ copies, never the live pages. source_refs and identity
frontmatter stay unchanged; external support is added through the credentialed citations. The first
--apply prepares the operation, and a later identical --apply commits only after full overlay lint.
Before preparation, declared citation-removal SHA values must be a subset of the current live page
citations; an unknown SHA fails closed before sidecar creation and reports the available source/URL summaries.
If the operation is committing, recover that operation before any ordinary lint. Do not use
revise-adopted for human-managed pages or as a substitute for a real book ingest.
To build the removal list mechanically instead of hand-writing digests, run the read-only exporter
(zero writes, no --request needed):
python scripts/pipeline.py revise-adopted --source <legacy_source> --emit-removal-sha <page>It prints every citation on the page as sha256 source=... title=... url=....
--source really scopes this path (the page's source_refs must name it, the same
predicate signing uses) and is mutually exclusive with --apply / --abort / --recover.
The request schema also accepts two optional, audited fields:
- page-level
frontmatter_updates.aliases.remove: [...]declares a controlled change of an immutable frontmatter key (currently onlyaliases). The authorization records both the expected post-update identity and the pre-update identity; the candidate must match the declared update — declaring without applying, or applying without declaring, both fail closed; - evidence
citation.urlis optional whencitation.sourceis a registered source_id (statesourcestable orsources/<id>.md); a URL, when present, must still be HTTPS.evidencemay be an empty list when the change is a pure citation removal or a body/meta edit with no new citations; the operation cannot complete until the candidate is genuinely edited (a byte-identical candidate stays in the prepared/waiting state), andreasonis the only justification record in that case.
7. Workflow
| Sub-unit | Input | Output | Acceptance | Persisted | Failure stop |
| R1 collect queue | Review-Queue + status | pending list | files and ledger aligned | — | queue missing |
| R2 classify | one item | lint/promotion/coverage/semantic/overwrite class | class maps to a fix path | analysis draft | type unclear |
| R3 suggest | item + related pages | fix/reject/promote suggestion | states risk, affected pages, commands | chat output | evidence thin |
| R4 user confirm | user decision | execute or reject | no target edit without confirmation; adopted legacy edits use a bounded revise-adopted request | Review-Queue mark / sidecar operation | human-page conflict |
| R5 verify loop | fix result | lint/rebuild/check result | the command passes or re-enqueues on failure | new proposal/mark | verify fails |
8. Failure stops / recovery
User has not confirmed; target managed_by: human; cross-domain promotion semantics unclear; a homonym
promotion; a lint fix would exceed the write scope; promote-concept or rebuild-registry fails; an item
lacks evidence; an adopted revision request is expired; an operation is already committing; a revert
target has changed since its recorded post. Recovery: unresolved items stay in Review-Queue with
their state. Abort an uncommitted prepared operation, recover a committing operation with its frozen
manifest, or use a new forward mode: edit after later live drift; then re-run the matching lint.
9. Acceptance criteria
- Every pending item has a class, a suggestion, and a user-decision state.
- No target vault page edited without user confirmation.
- A promotion-candidate has been judged "semantic reuse vs homonym".
- After a confirmed promotion,
promote-concept+rebuild-registrywere run. - After a lint-violation fix, the matching
lintwas re-run; failures stay in Review-Queue. - Adopted legacy fixes used
revise-adopted; their citations match the approved evidence and theirsource_refswere not changed by the authorization path. - No human page was auto-overwritten.
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.

