triage-resolve

Project- and tracker-agnostic engineering pipeline. Given a normalized work-item plus one or more targets ({repo, base, local checkout, site}), it implements the change with plan-with-docs + TDD in an isolated worktree, runs the REPO'S OWN declared verification (whatever its AGENTS.md / CLAUDE.md / cloud.md prescribes), then mandatory pipeline gates — an agent-browser visual regression for UI changes and `/simplify` + `/code-review` for code changes — then hands to the independent `triage-verifier` agent before opening a DRAFT pull request. For bug-kind items it propagates a verified fix to other sites that actually reproduce it. Returns PR URLs; performs no tracker calls. Usable standalone to resolve a branch against an AC checklist.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./triage-resolve/SKILL.md

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-sequenced, highly actionable engineering pipeline with strong validation checkpoints and feedback loops, scoring top marks on workflow clarity. Its weaknesses are repetition that hurts conciseness and a monolithic structure with no progressive disclosure via reference files.

Suggestions

De-duplicate the blocked-vs-humanFallback definition and the device/sim routing — state each once authoritatively and reference it, to tighten conciseness.

Split the dense device/sim-handling and bare-repo mechanics into a references/ file (e.g. ENVIRONMENT.md) and signal it one level deep from SKILL.md to improve progressive disclosure.

Optional: include a compact copy-pasteable command block for the most common single-site happy path to push actionability from 4 toward 5.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly assumes Claude's competence, but restates the blocked-vs-humanFallback distinction three times (intro, step 2.6, Guardrails) and the device/sim routing twice (step 2.4 and step 3), which is more than minor padding.	3 / 5
Actionability	Provides concrete executable guidance — exact git worktree commands, $AGENT_BROWSER_CDP_URL handling, agent-browser connect / next dev -H 0.0.0.0, /simplify, /code-review, gh pr create, and explicit JSON I/O schemas — with only minor gaps (e.g. full gh pr create flags).	4 / 5
Workflow Clarity	Clear numbered Isolate→Implement→Prove→Verify→Reconcile→Spread sequence with explicit validation checkpoints (repo loop until green, step-3 gates, verifier pass+no-gamingFlags gate), feedback loops (re-verify within retries), an AC checklist, and explicit abort/blocked handling — validation is pervasive so the destructive-cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist; the skill is a monolithic ~125-line SKILL.md with good section headers but inlined detail (device/sim routing, bare-repo mechanics) that could be split into references, and no signaled one-level-deep external references.	3 / 5
	Total	15 / 20 Passed

Description

63%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly specific and distinctive, laying out a concrete end-to-end engineering pipeline with clear actions and low conflict risk. Its main weaknesses are the absence of an explicit 'Use when...' trigger clause and an over-reliance on project-internal jargon over natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say (e.g. 'Use when resolving a work item into draft PRs across one or more repos, or verifying a branch against an acceptance checklist').

Replace or gloss internal jargon (normalized work-item, routing.map, triage-verifier) with plain-language equivalents so the description reads as natural triggers rather than pipeline internals.

Lead with a one-sentence plain-language summary of what the skill does before the mechanical detail, to anchor the 'what' for a reader skimming triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — implements changes via plan-with-docs+TDD, runs the repo's own verification, agent-browser visual regression for UI, /simplify + /code-review for code, hands to triage-verifier, opens a draft PR, and propagates fixes to reproducing sites — giving comprehensive coverage.	5 / 5
Completeness	The 'what' is detailed and explicit, but there is no 'Use when...' clause — only a weakly implied 'Usable standalone to resolve a branch against an AC checklist' — so per the missing-trigger-guidance cap completeness cannot exceed 3.	3 / 5
Trigger Term Quality	Contains a few relevant terms (DRAFT pull request, PR URLs, code/UI changes, TDD) but leans heavily on internal jargon (normalized work-item, triage-verifier, routing.map) rather than natural phrases a user would say, and is missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	The pipeline-specific machinery (worktrees, repo-declared verification, visual-regression + simplify/code-review gates, triage-verifier, bug-spread propagation) carves a clear niche with only minor overlap risk against other triage/pipeline skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MrToxy/claude-skills
Path: triage-resolve/SKILL.md
Commit: 66c7102

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.