investigate

Chain-loaded investigation. 5-phase Iron Law methodology with root cause gate.

Quality

63%

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/investigate/SKILL.md

Quality

Content

73%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 concise and gives concrete entry commands, and its structure is clean for a short skill. Its main weakness is workflow clarity: the multi-phase investigation sequence and its validation gate are entirely offloaded to an external chain JSON with no inline checkpoints.

Suggestions

Inline a brief summary of the 5-phase sequence with the 'root cause gate' as an explicit validation checkpoint, instead of deferring wholly to the chain JSON.

Add a feedback loop for the common failure case, e.g. what to do when a hypothesis is falsified or the root cause gate is not satisfied.

Clarify how the variables (root_cause, confidence) are set and where their values surface, to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is a lean ~6 lines with no over-explanation of concepts Claude already knows; every line carries an executable command or a necessary pointer, matching the lean-and-efficient anchor.	5 / 5
Actionability	Provides two copy-paste-ready `chain_loader start ...` commands with named entry variants, but leaves a minor gap on how the listed variables (root_cause, confidence) are produced or consumed.	4 / 5
Workflow Clarity	Only a rough entry-point choice (full vs. from-hypothesis) is shown; the actual 5-phase sequence and the 'root cause gate' validation are deferred to the chain JSON with no in-body checkpoints or error-recovery guidance.	2 / 5
Progressive Disclosure	Under 50 lines with no bundle files needed; content is cleanly organized into a heading and a bulleted command list, satisfying the simple-skill exception for progressive disclosure.	5 / 5
	Total	16 / 20 Passed

Description

53%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 names a specific methodology and niche but relies on branded jargon and omits any explicit trigger guidance. It is moderately specific and distinct but incomplete on the 'when to use' axis.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger situations (e.g., 'Use when diagnosing root causes of failures or debugging hard-to-reproduce issues').

Soften branded jargon ('Iron Law methodology', 'chain-loaded') with plain-language synonyms a user would actually say, like 'root cause analysis' or 'systematic debugging'.

Spell out 1-2 concrete actions the skill performs (e.g., 'tests hypotheses and gates on a confirmed root cause') to lift specificity from methodology-labeling to action-listing.

Dimension	Reasoning	Score
Specificity	Names the domain ('investigation') plus two concrete features ('5-phase Iron Law methodology', 'root cause gate'), but describes methodology rather than listing concrete actions, so it sits at the anchor-3 boundary rather than comprehensive coverage.	3 / 5
Completeness	States a clear-ish 'what' (chain-loaded investigation via a 5-phase methodology) but provides no 'when' / 'Use when...' trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Contains a couple of natural terms ('investigation', 'root cause') but mixes in branded jargon ('Iron Law methodology', 'chain-loaded') and misses common synonyms or variations users might say.	3 / 5
Distinctiveness Conflict Risk	The branded 'Iron Law methodology' and 'chain_loader' framing carve a fairly distinct niche with only minor overlap risk against generic debugging/investigation skills.	4 / 5
	Total	13 / 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/investigate/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.