CtrlK
BlogDocsLog inGet started
Tessl Logo

automagic-problem-discovery

Audit a workspace for recurring friction, pick the highest-leverage one, and build the automation that removes it. Use when the user asks "what should I automate", "what's wasting my time", "find the friction in my workflow", wants a self-improvement pass over their own tooling, or runs this on a recurring loop.

77

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An exceptionally well-structured instruction skill: concise, actionable, and rich with validation checkpoints and a hard destructive-action gate. The only gap is progressive disclosure — it leans monolithic with no reference files splitting out the longer prose.

Suggestions

Move the Gotchas and Loop mode sections into a separate references/ file (e.g. references/GOTCHAS.md) and link to it one level deep, keeping SKILL.md as a lean overview.

Verify the skills/FRAMEWORKS.md reference resolves to a real bundle file, or replace it with an in-skill pointer that does not depend on an external path.

Consider extracting the Step 6 held-action rules into a short reference checklist so the blast-radius gate is reusable and the main flow stays scannable.

DimensionReasoningScore

Conciseness

The body is dense and instruction-oriented ("Hunt repetition, not complaints"; "A half-built automation costs more than none") with no padding explaining concepts Claude already knows; every line earns its place.

5 / 5

Actionability

Though instruction-only, the guidance is concrete and executable throughout — "frequency-rank the shell history", "Run 5 Whys... three tiers minimum", "Rank by leverage times frequency", "fail loud (nonzero exit)", "hand back each held action as an exact command".

5 / 5

Workflow Clarity

Eight sequenced steps each end in an explicit "Done when..." checkpoint, Step 7 supplies verification (run twice, prove dedup, chase a surprising output to ground truth), and Step 6 is a hard validation gate for destructive actions — satisfying the destructive-operations cap.

5 / 5

Progressive Disclosure

Sections are well-organized with a See Also pointing to sibling skills and skills/FRAMEWORKS.md, but no bundle files exist and the ~140-line body inlines Gotchas and loop-mode prose that could live in one-level-deep reference files, leaving it slightly monolithic.

4 / 5

Total

19

/

20

Passed

Description

96%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 strong description: concrete actions, natural trigger phrasing, and explicit what/when guidance. Its only soft spot is a somewhat broad scope that could overlap with sibling automation skills.

DimensionReasoningScore

Specificity

"Audit a workspace for recurring friction, pick the highest-leverage one, and build the automation that removes it" names multiple concrete, comprehensive actions (audit, pick, build) within its niche, matching the score-5 anchor.

5 / 5

Completeness

It explicitly answers both what (audit/pick/build automation) and when via a concrete "Use when..." clause with multiple trigger phrases, satisfying the score-5 anchor.

5 / 5

Trigger Term Quality

It quotes natural user phrasing — "what should I automate", "what's wasting my time", "find the friction in my workflow", "self-improvement pass", "recurring loop" — giving comprehensive coverage of synonyms a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The recurring-friction/ledger niche is mostly distinct with specific triggers, but the broad "workspace friction" framing leaves minor overlap risk with related automation skills such as /debugging or /research.

4 / 5

Total

19

/

20

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
tslateman/duet
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.