skill-intake

Move incoming issues and pull requests through triage states until each is actionable or closed — use when the queue has piled up or a report arrives unsorted

Quality

83%

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

88%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.

A well-structured, lean triage skill with concrete commands, explicit stop/checkpoint rules, and a verification checklist. The main room for improvement is in actionability of the judgement-based steps and splitting detail into bundle files.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what issues, PRs, or triage are, and every section (When To Use, Stop rules, Output Contract) earns its place rather than padding context.	5 / 5
Actionability	Concrete commands are present throughout (`gh issue list`, `gh pr list`, `bd ready`, `gh issue edit --add-label`, `bd update`) plus a copy-paste comment-posting block, but the categorise/verify/brief steps are judgement guidance rather than executable code, leaving minor gaps.	4 / 5
Workflow Clarity	A clearly sequenced 5-step workflow with explicit validation checkpoints (the Verify step, the Stop Or Checkpoint Rules) and a closing Verification checklist; because validation is present for the destructive/batch moves (closing, labelling), the missing-validation cap does not apply.	5 / 5
Progressive Disclosure	Well-organized into clear sections with only one-level cross-references to sibling skills (no nested detail chains), but at ~130 lines with no bundle files to offload detail into, it does not qualify for the simple-skill 5 and has minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

78%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, third-person description that clearly states both capability and trigger conditions with natural phrasing. Its only weakness is that it describes a single composite action rather than enumerating several specific capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain (issues and pull requests) and one concrete composite action ('Move ... through triage states until each is actionable or closed'), but does not enumerate several distinct actions, so it stops at '1-2 concrete actions' rather than the multi-action anchor above.	3 / 5
Completeness	Explicitly answers both what ('Move incoming issues and pull requests through triage states ...') and when ('use when the queue has piled up or a report arrives unsorted') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases ('use when the queue has piled up or a report arrives unsorted') read as things a user would say, but common synonyms like 'issues', 'PRs', or 'triage' itself are absent, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The triage niche is clear and distinct from generic skills, but there is minor overlap risk with related issue/PR skills (skill-issues, skill-code-review) referenced in the body, so it does not fully reach minimal-conflict.	4 / 5
	Total	16 / 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: nyldn/claude-octopus
Path: skills/skill-intake/SKILL.md
Commit: 0093dab

Reviewed: 5 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.