CtrlK
BlogDocsLog inGet started
Tessl Logo

autonomous-coding-workflow

Governs safe, incremental, repository-wide development workflow with continuous validation gates

51

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/autonomous-coding-workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is a well-sequenced, validation-driven workflow with strong feedback loops, but it is a monolithic instruction file with repeated validation steps and a mix of concrete commands and abstract directives. Splitting detailed material into reference files and de-duplicating the validation checks would improve it.

Suggestions

Consolidate the repeated php -l / Pint / targeted-test checks into a single validation section referenced by sections 4, 5, and 6 to remove redundancy.

Move refactoring heuristics and the success-criteria checklist into a separate reference file (e.g., REFACTORING.md) linked from the body, enabling progressive disclosure.

Tighten abstract directives like "Understand current behavior" and "Preserve existing architectural patterns" with concrete, checkable acceptance criteria.

DimensionReasoningScore

Conciseness

The body is mostly lean and directive without explaining concepts Claude already knows, but the php -l / Pint / targeted-tests checks recur across sections 4, 5, and 6, so it could be tightened by consolidating the repeated validation lists.

2 / 3

Actionability

It supplies concrete executable commands ("php -l", "vendor/bin/pint --dirty --format agent", "migrate:fresh --seed") and specific file paths, but much of the guidance is abstract directive ("Understand current behavior", "Preserve existing architectural patterns") without concrete acceptance criteria.

2 / 3

Workflow Clarity

The eight numbered sections form a clear sequence with explicit validation gates ("Never proceed if any of the following fail"), feedback loops ("Fix failures immediately", "Continue only if repository is clean"), and a closing checklist (Success Criteria), matching the level-3 anchor.

3 / 3

Progressive Disclosure

Content is well-organized into labeled sections, but everything lives in a single ~138-line monolithic file with no external references or file splits, so material such as refactoring heuristics and success criteria that could be separate remains inline.

2 / 3

Total

9

/

12

Passed

Description

50%

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 conveys a clear domain and a few defining characteristics but is abstract and lacks any usage trigger. Adding a concrete "Use when..." clause with natural trigger terms would lift both completeness and trigger-term quality.

Suggestions

Add an explicit "Use when..." clause stating when Claude should invoke this skill (e.g., "Use when making repository-wide code changes or multi-module refactors").

Replace the abstract verb "Governs" with concrete actions users would recognize, such as "Refactor, test, and commit repository-wide code changes incrementally".

Include natural trigger terms users actually say (e.g., "refactor", "repository-wide changes", "run the test suite", "commit a module") to improve distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ("repository-wide development workflow") and some characteristics ("incremental", "continuous validation gates"), but the verb "Governs" is abstract and it lists no concrete actions, so it stops short of the multi-action level-3 anchor.

2 / 3

Completeness

It states what the skill does but provides no "when" guidance — there is no "Use when..." clause or equivalent trigger, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Relevant keywords like "development workflow", "repository-wide", and "validation" are present, but phrasing such as "Governs" and "continuous validation gates" leans technical and misses the natural terms a user would actually say.

2 / 3

Distinctiveness Conflict Risk

"repository-wide development workflow with continuous validation gates" carves out a somewhat specific niche, but "development workflow" is broad enough to overlap with other coding skills and there are no distinct triggers to prevent confusion.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Bottelet/DaybydayCRM
Reviewed

Table of Contents

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.