Tessl • The management layer for AI agent skills

SkillPublic

triage

Triage a GitHub issue or a reported problem — check it is real and not by design (code, git history, PRs, Hindsight memory), find the code and patterns to reuse, build a proof-of-concept fix and prove it solves the problem, then explain the problem and the fix in behaviours before doing the full fix. Use when asked to "triage

Quality

93%

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

Quality

Content

96%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 body is a model instruction-only skill: dense with executable commands, explicit validation gates, and no filler. The only structural refinement available is splitting the environment-specific detail (pg0 instances, ports, service cleanup) into a reference file now that it approaches 100 lines.

Dimension	Reasoning	Score
Conciseness	Lean imperative prose with no explanations of concepts Claude already knows; every section carries repo-specific rules ('No numbers, no plan.', 'never pkill -f hindsight/pytest'). The longer 'No workarounds' paragraph is substantive policy with concrete examples, not padding, so it fits the lean anchor rather than the minor-trimming one.	5 / 5
Actionability	Fully executable guidance throughout: 'gh issue view <N> --comments', 'git log -S '<key string>' --oneline', 'gh pr list --state all --search "<keywords>"', branch naming 'triage/<issue-number-or-short-slug>', 'lsof -nP -iTCP:<port> -sTCP:LISTEN', 'HINDSIGHT_API_DATABASE_URL=pg0://triage-<slug>', 'pg0 drop --name <name> -f', plus a ready-to-post close-comment template.	5 / 5
Workflow Clarity	Five clearly sequenced sections with an explicit termination point ('It ends at step 5, with the user's answer') and explicit validation checkpoints: reproduction 'fails before the change and passes after it', 'Nearby tests still pass', 'Try the other paths you found in step 3', 'Ask before posting or closing', and the final AskUserQuestion gate before any full fix.	5 / 5
Progressive Disclosure	Well-organized single-file body with a clearly signaled one-level reference to '.claude/skills/code-review/SKILL.md'. No bundle files exist, and at ~95 lines the perf/UI/pg0-services subsections carry detail that could arguably live in a reference file — good structure with minor placement gaps rather than a fully optimal split.	4 / 5
	Total	19 / 20 Passed

Description

88%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.

A strong description: third-person, specific, and complete with explicit quoted trigger phrases. Its only weaknesses are a few missing natural trigger synonyms and a mildly generic trigger phrase that could overlap with general debugging skills.

Suggestions

Add one or two more natural trigger synonyms (e.g. 'investigate this issue', 'reproduce this bug', 'can you check #N') to the 'Use when' clause for broader keyword coverage.

Sharpen the 'look into this issue' trigger toward issue triage (e.g. 'look into this GitHub issue') to reduce overlap with general debugging skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions covering the full workflow — 'check it is real and not by design (code, git history, PRs, Hindsight memory)', 'find the code and patterns to reuse', 'build a proof-of-concept fix and prove it solves the problem', 'explain the problem and the fix in behaviours' — with mechanisms named, matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (the full first sentence describing the triage workflow) and 'when' ('Use when asked to "triage #N", "look into this issue", or "is this a real bug"') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Concrete quoted triggers — 'triage #N', 'look into this issue', 'is this a real bug' — are natural user phrasings, but common synonyms like 'investigate this issue' or 'reproduce this bug' are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The niche — issue triage ending at a POC and user decision, not the full fix — is distinct, but the trigger 'look into this issue' is generic enough to also reach a general debugging or bug-fixing skill, giving minor overlap risk.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: vectorize-io/hindsight
Path: .claude/skills/triage/SKILL.md
Revision: b4a0da1

Reviewed: 5 days ago

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.

triage

Table of Contents

Is this your skill?