CtrlK
BlogDocsLog inGet started
Tessl Logo

compound

Use when a problem has just been solved and verified working — the fix is fresh, the investigation is in recent history, and the solution is non-trivial enough to capture for future reference

64

Quality

75%

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 ./skills/compound/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-structured, actionable skill body that uses tables and explicit phase sequencing effectively and enforces its single-file-write invariant via a critical-requirement block and a Common Mistakes table. Main gaps are the unspecified YAML frontmatter schema and subagent prompt contents, and the validation step being named rather than executable.

Suggestions

Specify the required YAML frontmatter fields (e.g. category, component, date) so the 'Validate YAML frontmatter' step is executable rather than a checklist item.

Either inline minimal subagent prompt skeletons or point to where their prompts live, so the Phase 1 launch is copy-paste ready.

Give the compact-safe mode a concrete filename pattern so its single-pass write path matches the full-mode output location.

DimensionReasoningScore

Conciseness

The body is dense and mostly token-efficient with tables doing heavy lifting, but phrases like 'Captures problem solutions while context is fresh, creating structured documentation in docs/solutions/ with YAML frontmatter for searchability' slightly restate what the description already covered.

4 / 5

Actionability

Concrete invocation syntax, exact output paths, category lists, and a per-subagent return table give executable guidance; gaps are that subagent prompts and the YAML frontmatter schema are referenced but not specified, so Claude must infer their exact contents.

4 / 5

Workflow Clarity

Sequencing is explicit (Phase 0.5 -> Phase 1 parallel -> WAIT -> Phase 2 -> Phase 2.5 -> Phase 3) with a critical-requirement callout and a clear Common Mistakes table; the cap-relevant destructive/batch write step does have a 'Validate YAML frontmatter' checkpoint, though the validate step is named rather than given an executable command.

4 / 5

Progressive Disclosure

No bundle files exist, yet the content is well-organized into clearly headed sections (Overview, When to Use, Quick Reference, Implementation, Common Mistakes) with a compact-safe mode sectioned off; scored against actual bundle structure (empty), it stays one level deep and navigable, with only minor inlining of the phase tables.

4 / 5

Total

16

/

20

Passed

Description

75%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, mostly-concrete description that clearly states both purpose and timing, with a coherent third-person voice. Its main weakness is describing the internal orchestration mechanism more than the user-facing outcome, and keeping the most natural trigger phrases in the body instead of the description.

Suggestions

Lead the description with the user-facing outcome ('Document verified problem solutions into searchable docs/solutions/ files') before the internal mechanism.

Surface natural trigger phrases ('that worked', 'it's fixed', 'problem solved') directly in the description rather than only in the body's When-to-Use section.

DimensionReasoningScore

Specificity

Names the domain (capturing problem solutions into structured docs) and several concrete actions (gather context, extract solution, find related docs, develop prevention, classify category), but the description focuses on the meta-process rather than the artifact produced.

4 / 5

Completeness

Explicitly answers both what (capture problem solutions into structured docs with YAML frontmatter) and when (problem just solved and verified, fix fresh, non-trivial), though the 'when' is a clause rather than a crisp 'Use when...' phrase.

4 / 5

Trigger Term Quality

Good natural trigger phrasing around 'just been solved and verified working' and 'fix is fresh', but lacks the short colloquial phrases a user would actually utter like 'that worked' or 'it's fixed' that appear only in the body.

4 / 5

Distinctiveness Conflict Risk

The post-solution-fresh-context niche is fairly distinct from other doc-writing skills, but the boundary against general documentation skills is implicit rather than sharply drawn.

4 / 5

Total

16

/

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
lucianghinda/superpowers-ruby
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.