creating-debug-tests-and-iterating

Use this skill when faced with a difficult debugging task where you need to replicate some bug or behavior in order to see what is going wrong.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agency/plugins/nori/skills/creating-debug-tests-and-iterating/SKILL.md

Quality

Content

61%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 content is lean and provides a clear iterated debug loop with a feedback cycle, which is the skill's core value. Its weaknesses are incomplete actionability in the API case and only moderate progressive-disclosure structure, with one prose reference instead of clearly signaled sub-files.

Suggestions

Add one concrete API-call example (e.g. a curl or requests snippet) instead of leaving the API section at 'scripting language of choice'.

Insert an explicit checkpoint in the loop, e.g. 'Only proceed to fixing once the debug script reliably reproduces the bug.', to strengthen validation.

Convert the webapp-testing pointer into a clear link and consider splitting the CLI/API/TUI emulator guidance into a short references file if the skill grows.

Dimension	Reasoning	Score
Conciseness	The body is short and assumes Claude's competence, with no padding explaining what debugging or subprocesses are; only the three near-duplicate CLI snippets (bash/python/node) for the same trivial call add mild redundancy.	4 / 5
Actionability	It gives some concrete code (subprocess.run, exec, server start commands) but the core loop is described as imperatives ('Add many logs', 'Analyze the output') without executable specifics, and the API section ends on 'scripting language of choice' with no concrete call example.	3 / 5
Workflow Clarity	The numbered list lays out a clear loop (add logs -> run -> analyze -> update -> fix -> clean up) with a stop condition, which is a genuine feedback loop for a debugging task; minor validation gaps (no explicit checkpoint that the bug is actually reproduced before fixing) keep it just below 5.	4 / 5
Progressive Disclosure	Structure is present with headed sections and a single one-level reference (the webapp-testing SKILL.md pointer), but there are no bundle files and the referenced path is described in prose rather than as a clear navigable link, so organization is only adequate.	3 / 5
	Total	14 / 20 Passed

Description

61%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 clearly states a trigger ('Use when faced with a difficult debugging task') and a concrete purpose (replicating a bug to observe what goes wrong), giving it solid completeness and distinctiveness. It is limited by thin action specificity and incomplete trigger-term coverage (missing synonyms like 'reproduce' or 'troubleshoot').

Suggestions

Enumerate the concrete actions the skill performs, e.g. 'Write an external debug script, add logs, and loop until the bug is reproduced and fixed'.

Add natural trigger synonyms such as 'reproduce', 'troubleshoot', or 'hard-to-reproduce bug' so users phrasing the need differently still surface the skill.

Tighten the 'when' clause with a more specific trigger condition, e.g. 'Use when a bug is hard to trigger from existing tests and you need a standalone reproduction.'

Dimension	Reasoning	Score
Specificity	It names the debugging domain and one concrete action ('replicate some bug or behavior'), but offers no enumeration of the distinct actions the skill performs, so it falls at the '1-2 concrete actions' anchor rather than higher.	3 / 5
Completeness	It states what the skill does ('replicate some bug or behavior in order to see what is going wrong') and gives an explicit 'when' trigger ('Use this skill when faced with a difficult debugging task'), satisfying both anchors, though the 'when' could be more specific about trigger conditions.	4 / 5
Trigger Term Quality	Natural phrases like 'debugging task', 'replicate some bug', and 'see what is going wrong' map to user language, but common synonyms such as 'troubleshoot', 'reproduce', or 'flaky test' are missing, placing it at 'some relevant keywords' rather than full coverage.	3 / 5
Distinctiveness Conflict Risk	The framing of a difficult debugging task where you must replicate behavior is a fairly distinct niche that is unlikely to collide with most other skills, with only minor overlap risk against general testing skills.	4 / 5
	Total	14 / 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: microsoft/FluidFramework
Path: .agency/plugins/nori/skills/creating-debug-tests-and-iterating/SKILL.md
Commit: f02e424

Reviewed: 3 days 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.