github-wake

Register an existing GitHub issue so the current Codex or Claude Code session is woken when its first future comment arrives. Use when work is genuinely blocked on a GitHub reply and the session must resume asynchronously.

Quality

81%

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.

The body is a lean, actionable, single-purpose skill with executable commands, explicit preconditions, and sensible guardrails against misuse. The only nits are an inlined version number and the absence of section sub-headers.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence (no explanation of GitHub/comments), and every prose line carries specific do/don't guidance; the inlined version requirement "Claude Code 2.1.98 or later" is time-sensitive and not isolated in a deprecated section, keeping it just below a 5.	4 / 5
Actionability	Copy-paste-ready commands cover the common cases — `github-wake ISSUE_URL`, `github-wake --claude-monitor ISSUE_URL`, `--status`, `--cancel WATCH_ID` — and each is fully executable with concrete argument forms.	5 / 5
Workflow Clarity	As a single-action skill the action is unambiguous, with explicit precondition gates ("only when both of these are true", "must also have been launched through codex-dynamic") and a recovery path (Monitor unavailable → upgrade rather than poll), satisfying the simple-skill exception.	5 / 5
Progressive Disclosure	Under 50 lines with no external references and a logical flow of grouped command blocks, it is well organized; the lack of any ## sub-headers is a minor organization gap that keeps it from a clean 5.	4 / 5
	Total	18 / 20 Passed

Description

73%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 third-person, specific, and clearly distinguishes the skill with an explicit Use-when clause. Its weakest area is capability breadth — it describes essentially one action without surfacing the management surface (status, cancel).

Suggestions

Mention the management actions (e.g. checking status, canceling a watch) in the description so the capability list reads as more than a single action.

Soften the abstract gating in the Use-when clause with a concrete user-facing trigger phrase (e.g. "Use when the user says they are blocked on a GitHub reply").

Consider adding the natural term "notification" or "watch" to broaden trigger keyword coverage.

Dimension	Reasoning	Score
Specificity	"Register an existing GitHub issue so the current Codex or Claude Code session is woken when its first future comment arrives" names the domain and one concrete action, but does not enumerate multiple capabilities (e.g. status, cancel) — matching the 1-2 concrete actions anchor rather than comprehensive coverage.	3 / 5
Completeness	It has an explicit "Use when work is genuinely blocked on a GitHub reply and the session must resume asynchronously" clause plus a clear "what", but the when-condition is somewhat abstract/gated rather than concrete user-utterance triggers, so it is not a clean 5.	4 / 5
Trigger Term Quality	Natural terms like "GitHub issue", "GitHub reply", "comment", and "blocked" are phrases a user would say, giving good coverage; a few common variants (e.g. "notification", "watch") are absent, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	"Register an existing GitHub issue so the session is woken when its first future comment arrives" carves a clear niche (async reply wakeup for a coding session) with distinct triggers and minimal overlap with other skills.	5 / 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: pchalasani/claude-code-tools
Path: plugins/dynamic-workflow/skills/github-wake/SKILL.md
Commit: ee0f309

Reviewed: 3 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.