workflow-test-fix

Chain-loaded test-fix pipeline. 5-phase test generation and iterative execution.

Quality

54%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/workflow-skills/workflow-test-fix/SKILL.md

Quality

Content

58%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 admirably lean and its two entry commands are immediately runnable, but it delegates a supposedly 5-phase workflow to an external directory it never describes, lists configuration variables with no usage syntax, and offers no sequence or validation checkpoints for the iterative test-fix cycle. It works as a launcher stub, not as a skill body.

Suggestions

Show how the variables are actually passed, e.g. `chain_loader start --chain=workflow-test-fix --var goal=<goal> --var auto_yes=true`, so the commands cover the parameterized cases.

Enumerate the 5 phases (or at least name them and where each lives) instead of pointing at an opaque directory, and state what 'execute-only' skips so entry-point choice is informed.

Since the pipeline iteratively executes and fixes, add an explicit stopping condition or validation checkpoint (e.g. 'loop generate → run → fix until all tests pass, max N iterations').

Dimension	Reasoning	Score
Conciseness	Six lines, zero padding, no explanation of concepts Claude already knows — every line is either a command, a pointer, or a variable list. This matches the 'lean and efficient; every token earns its place' anchor exactly.	5 / 5
Actionability	The two `chain_loader start` commands are copy-paste ready, but 'Variables: session_id, goal, auto_yes' gives no syntax for how to pass them, and 'Phases from .claude/skills/workflow-test-fix/phases/' points at content without saying how it is consumed. Concrete commands exist but key details for parameterized use are missing, which is the anchor-3 fit; the variable wiring gap is more than 'minor', so not a 4.	3 / 5
Workflow Clarity	The skill is described as a '5-phase' pipeline, yet no phases, sequence, or checkpoints appear in the body — only two entry-point commands and a directory pointer. This is a rough entry surface with many gaps and no validation guidance for the iterative fix cycle, matching anchor 2; it cannot reach 3 because no steps are actually listed.	2 / 5
Progressive Disclosure	Content is appropriately short and the phases reference is only one level deep, but the pointer is a bare, unlinked path (`.claude/skills/workflow-test-fix/phases/`) that does not exist in the skill's bundle, and the body has no section headers or per-phase navigation. 'References present but not clearly signaled' fits anchor 3; not a 4 because the reference is neither verified nor well-signaled.	3 / 5
	Total	13 / 20 Passed

Description

50%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 terse and names a recognizable domain, but it relies on internal jargon ('chain-loaded', '5-phase') without saying what the phases do, provides no 'when to use' trigger guidance, and lacks the natural terms a user would say when needing this skill. It reads as an index entry rather than a self-contained capability description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to generate tests for a change and iteratively fix failures until the suite passes.'

Replace or gloss internal jargon ('chain-loaded') and include natural trigger terms users would actually say: 'write tests', 'failing tests', 'test suite', 'fix until green'.

Briefly name the 5 phases (or their outcomes) so the 'what' is concrete rather than a bare phase count.

Dimension	Reasoning	Score
Specificity	The description names its domain ('test-fix pipeline') and 1-2 concrete actions ('5-phase test generation and iterative execution'), but does not enumerate what the phases or actions actually are, matching the anchor for domain plus 1-2 actions without comprehensiveness. It is not a 4 because it never lists several specific actions with only minor gaps.	3 / 5
Completeness	It conveys a partial 'what' ('5-phase test generation and iterative execution') but has no 'when' trigger clause at all — the guidelines cap completeness at 3 for a missing 'Use when...' equivalent. Not a 4 because even a weakly implied 'when' is absent.	3 / 5
Trigger Term Quality	'test' and 'test-fix' are relevant keywords, but 'chain-loaded' is internal jargon a user would never say, and natural phrasings like 'write tests', 'fix failing tests', or 'run the test cycle' are absent. This sits at 'some relevant keywords but missing common variations', not a 4 which requires only a few natural terms missing.	3 / 5
Distinctiveness Conflict Risk	'test-fix pipeline' carves out a niche, but the description could plausibly overlap with generic test-running or CI-fix skills, and 'chain-loaded' obscures the boundary rather than sharpening it. This is 'somewhat specific but could still overlap', short of the mostly-distinct anchor 4.	3 / 5
	Total	12 / 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: catlog22/Claude-Code-Workflow
Path: .claude/workflow-skills/workflow-test-fix/SKILL.md
Commit: 07491b0

Reviewed: 3 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.