CtrlK
BlogDocsLog inGet started
Tessl Logo

ac-config-manager

Configuration management for autonomous coding. Use when loading settings, managing environment variables, configuring providers, or setting up autonomous mode options.

54

Quality

68%

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/ac-config-manager/SKILL.md

The canonical home for this skill is ac-config-manager in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 actionable, with concrete and verified API examples and precise configuration tables, and it contains no concept-padding. However, it suffers from duplicated load/default sections, lacks a sequenced workflow with validation checkpoints, and — most seriously — four of its referenced bundle files do not exist.

Suggestions

Fix the dangling references: create `references/CONFIG-SCHEMA.md` and `references/ENVIRONMENT.md` (or remove them), and correct the Scripts list since only `scripts/config_manager.py` exists.

Consolidate duplication: merge the Quick Start code examples with the Operations section, and unify the JSON schema block with the Default Values table.

Add a validation checkpoint to the workflow, e.g. 'After update() or create_default_config(), run validate() and fix any errors before proceeding'.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and uses efficient tables and code, but it is noticeably duplicated: 'Load Configuration' appears in both Quick Start and Operations, and defaults for max_iterations, max_cost_usd, etc. appear in both the JSON schema block and the Default Values table — more than minor trimming would fix.

3 / 5

Actionability

Concrete Python snippets map to real, verified methods in scripts/config_manager.py (load, create_default_config, update, validate, get_memory_config, get_build_config, get_paths), and tables give exact variable names and defaults. Minor gaps keep it from fully copy-paste ready: `project_dir` is never defined or imported in the snippets, and no CLI usage is shown.

4 / 5

Workflow Clarity

Operations are numbered 1-4 and a validation operation with an error loop exists, but the sections form an API tour rather than a sequenced workflow — there is no guidance on when to validate (e.g. 'run config.validate() after update() before proceeding') or how the operations chain together.

3 / 5

Progressive Disclosure

Sectioning is decent and references are one level deep, but the referenced files `references/CONFIG-SCHEMA.md` and `references/ENVIRONMENT.md` do not exist in the bundle, and `scripts/config_schema.py` and `scripts/path_manager.py` listed under Scripts are also missing — navigating to the detail material fails, which is worse than references merely being unclear.

2 / 5

Total

12

/

20

Passed

Description

71%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.

A solid description with an explicit 'Use when...' trigger clause and several concrete actions, written in appropriate third-person style. Its main weaknesses are a high-level 'what' statement, missing common trigger variations, and overlap risk with generic configuration-management skills.

Suggestions

Differentiate from generic config skills by anchoring triggers to the specific artifact, e.g. 'Use when setting up or editing .claude/autonomous-config.json for autonomous coding runs'.

Sharpen the 'what' by enumerating core capabilities: loading and merging defaults/env vars/config file, validating settings, and managing provider and safety-limit configuration.

Add natural trigger variations users might say, such as 'config file', 'change settings', or 'budget limit'.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'loading settings', 'managing environment variables', 'configuring providers', 'setting up autonomous mode options' — which goes beyond the 1-2 actions of a score-3 anchor, but is not comprehensive since it omits validation, path management, and budget limits covered by the skill.

4 / 5

Completeness

It has both a clear 'what' ('Configuration management for autonomous coding') and an explicit 'when' clause ('Use when loading settings, managing environment variables, configuring providers, or setting up autonomous mode options'), but the 'what' is a high-level category rather than the enumerated capabilities a score-5 example provides.

4 / 5

Trigger Term Quality

Natural phrases users would say ('load settings', 'environment variables', 'configure providers') are present, matching good keyword coverage, but common variations like 'config file', 'change settings', or the concrete filename 'autonomous-config.json' are missing, so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

'Configuration management' with triggers like 'loading settings' and 'environment variables' overlaps heavily with generic configuration and settings skills; only the 'autonomous coding' / 'autonomous mode' scoping narrows it, leaving it somewhat specific but still prone to overlap with similar skills rather than mostly distinct.

3 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.