fetch-ci-build

Fetch CI build results and diagnose failures. Auto-detects provider from project files or URLs. Supports GitHub Actions, Buildkite, and CircleCI.

1.67x

Quality

68%

Does it follow best practices?

Impact

92%

1.67x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-mikeastock/skills/fetch-ci-build/SKILL.md

Quality

Content

71%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 well-structured with clear navigation to real reference files and a sequenced workflow that asks before applying fixes. The main improvements are removing the redundant workflow diagram and trimming tables that belong in the references.

Suggestions

Remove or condense the Graphviz 'workflow' block since the Step-by-Step Process already covers the same sequence.

Move the Error Types and Common Mistakes tables into the provider reference files to keep SKILL.md a lean overview.

Add an explicit post-fix verification step (e.g., re-run the failing job or run tests locally) as a workflow checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tables, executable bash, lists), but the Graphviz workflow diagram duplicates the 'Step-by-Step Process' that immediately follows, and the Error Types/Common Mistakes tables could live in the provider references.	3 / 5
Actionability	Provides executable detection commands and links to concrete reference files with real commands, though the actual fetch logic for Buildkite/CircleCI is delegated to the scripts rather than shown inline.	4 / 5
Workflow Clarity	A clear 7-step sequence is presented both as a diagram and a numbered list, with an explicit 'Ask: Apply fix?' checkpoint before any change; minor validation gaps remain (e.g., no re-run/verify step after applying a fix).	4 / 5
Progressive Disclosure	SKILL.md is a concise overview with well-signaled one-level-deep references to github.md, buildkite.md, and circleci.md (all present) plus scripts, with bulk provider detail appropriately split out.	5 / 5
	Total	16 / 20 Passed

Description

65%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 clear and specific about the CI-build domain and supported providers, with a distinct niche. Its main weakness is the absence of any explicit 'Use when...' trigger guidance, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when diagnosing CI failures, broken builds, or failed test runs.'

Expand the action list to cover the full capability set (extract errors, suggest fixes) rather than just fetch and diagnose.

Include natural synonyms users say, such as 'failed tests', 'broken build', or 'red CI'.

Dimension	Reasoning	Score
Specificity	Names the CI domain and two concrete actions ('Fetch CI build results and diagnose failures'), but does not enumerate the full set of capabilities (e.g., error extraction, fix suggestions), so coverage is not comprehensive.	3 / 5
Completeness	It clearly states what the skill does, but provides no 'Use when...' trigger clause, so per the rubric guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('CI build results', 'diagnose failures') plus concrete provider names (GitHub Actions, Buildkite, CircleCI), though common variants like 'failed tests', 'broken build', or 'red CI' are absent.	4 / 5
Distinctiveness Conflict Risk	The CI-build niche and named providers (GitHub Actions, Buildkite, CircleCI) give it distinct triggers with minimal overlap risk against other skills.	5 / 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: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-mikeastock/skills/fetch-ci-build/SKILL.md
Commit: 6453c0b

Reviewed: about 10 hours 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.