Tessl • The management layer for AI agent skills

SkillPublic

gha-checks

Check GitHub Actions CI status for PRs and branches. Use when the user asks "did CI pass", "check status", "what failed", "are checks green", "PR checks", "CI status", "workflow status", "re-run jobs", or wants a quick summary of GitHub Actions runs for a PR or the current branch.

Quality

75%

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 ./.claude/skills/gha-checks/SKILL.md

Quality

Content

51%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 two-line delegation stub: maximally lean, but it carries none of the skill's actual guidance — every command, workflow step, and validation checkpoint is deferred to a shared skill file outside the bundle that cannot be verified here. As written it is a clear pointer, not a self-contained, actionable skill.

Suggestions

Inline a minimal quick-start with the core commands (e.g., `gh pr checks <PR-number>`, `gh run list --branch <branch>`, `gh run view <run-id> --log-failed`) so the skill remains actionable even when the shared skill file is unavailable.

Sketch the workflow in the body — check status, summarize failures, optionally re-run (`gh run rerun <run-id> --failed`), then verify the re-run succeeded — so the sequence and its validation step are visible without loading the external file.

Reference the shared skill via a bundle-relative path (or vendor it under references/) instead of the absolute `~/.agents/skills/gha-checks/SKILL.md`, so the delegation target resolves from the skill bundle itself.

Dimension	Reasoning	Score
Conciseness	The entire body is "Load and follow the shared skill at `~/.agents/skills/gha-checks/SKILL.md`" plus a one-line provenance comment — no padding and no explanation of concepts Claude already knows; every token earns its place, matching the level-5 anchor.	5 / 5
Actionability	The only instruction is "Load and follow the shared skill at ..." — concrete as a directive, but it defers every step of the actual task and contains no command or code for checking CI status, matching level 2 ("minimal concrete guidance; missing the specific steps to execute"). It is above level 1 because the pointer itself is specific and instructive rather than vague.	2 / 5
Workflow Clarity	No sequence for the actual task (check status, summarize failures, re-run jobs) appears in the body; the single delegation step is unambiguous, but all task steps and any validation (e.g., confirming a re-run succeeded) are pushed into an external file — fitting level 2 ("steps poorly defined; validation absent") rather than level 1, since the one written instruction is coherent.	2 / 5
Progressive Disclosure	The reference is one level deep and clearly signaled, but the body contains no overview content at all, and the target `~/.agents/skills/gha-checks/SKILL.md` lies outside the bundle (no references/, scripts/, or assets/ exist, and the absolute path does not resolve in this environment) — "could be better organized" fits level 3; not level 4, because no content is appropriately placed within this skill and the reference cannot be verified from the bundle.	3 / 5
	Total	12 / 20 Passed

Description

90%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 strong: it states a concrete capability, anchors it to a narrow GitHub Actions CI niche, and provides an explicit 'Use when' clause with many natural trigger phrases. Its only weakness is that the what-clause names just 1-2 actions, leaving the full scope (e.g., re-running jobs, inspecting failure logs) to be inferred from trigger phrases rather than stated.

Dimension	Reasoning	Score
Specificity	"Check GitHub Actions CI status for PRs and branches" and "a quick summary of GitHub Actions runs" name the domain plus 1-2 concrete actions, matching the level-3 anchor ("Processes PDF files and extracts content"). It stays below level 4 because no several-action list is stated — "re-run jobs" appears only as a trigger phrase, not as an explicit capability.	3 / 5
Completeness	"Check GitHub Actions CI status for PRs and branches" explicitly states the what, and "Use when the user asks \"did CI pass\", ... " gives the when with concrete trigger phrases — both questions clearly and explicitly answered, matching the level-5 anchor exactly (and above level 4, where the when is only loosely specified).	5 / 5
Trigger Term Quality	The trigger list — "did CI pass", "what failed", "are checks green", "PR checks", "CI status", "workflow status", "re-run jobs" — comprehensively covers the natural phrases and synonyms (checks/CI/workflow) users would actually say, matching the level-5 anchor; at most near-synonyms like "build status" are missing.	5 / 5
Distinctiveness Conflict Risk	The niche "GitHub Actions CI status for PRs and branches" is narrow and the triggers ("CI status", "are checks green", "PR checks") are domain-anchored, giving minimal conflict risk — a clear level-5 fit rather than level 4's "minor overlap risk with closely related skills".	5 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: phatblat/dotfiles
Path: .claude/skills/gha-checks/SKILL.md
Revision: 4d65cab

Reviewed: 8 hours 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.

gha-checks

Table of Contents

Is this your skill?