CtrlK
BlogDocsLog inGet started
Tessl Logo

decision-capture

Detect decisions in conversation and record them with rationale, alternatives, and outcome tracking.

57

Quality

66%

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/decision-capture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable and well-structured, with a concrete template, exact write targets, a mandatory execution order, and validation plus outcome-tracking feedback loops. The only meaningful gap is the absence of explicit error-recovery guidance when a memory_write fails.

DimensionReasoningScore

Conciseness

The body is mostly lean with concrete templates and exact paths, but the opening "Decisions are durable knowledge — they explain why a path was chosen..." is mild motivational padding Claude could infer, keeping it just below a 5.

4 / 5

Actionability

It provides a complete copy-paste-ready decision template with frontmatter fields, exact memory_write call targets, precise file paths, and a mandatory numbered execution order that covers the common recording cases.

5 / 5

Workflow Clarity

A clear mandatory sequence (write decision → optional follow-on writes → only then confirm) with an explicit validation gate (never confirm unless memory_write succeeded) and an outcome-tracking feedback loop, but no retry/error-recovery guidance on a failed write.

4 / 5

Progressive Disclosure

Content is well-organized into clear sections (Detection, Recording, Follow-through, Outcome tracking, Confirmation) with no external references needed; the inline template is reasonable, though the skill sits above the under-50-line simple-skill threshold.

4 / 5

Total

17

/

20

Passed

Description

51%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 conveys a clear purpose and concrete actions but omits any explicit "when to use" trigger guidance and lacks natural user phrasing. Adding a "Use when..." clause with real trigger phrases would lift the completeness and trigger-term dimensions.

Suggestions

Append a trigger clause such as "Use when the user says 'we decided', 'going with', 'record this decision', or wants a decision logged with rationale."

Include natural synonyms users say (decided, chose, settled on, went with) directly in the description rather than only in the activation keywords.

Tighten the action list into one comprehensive enumeration (detect, persist, link follow-on commitments, schedule outcome follow-up) to reach full specificity.

DimensionReasoningScore

Specificity

"Detect decisions in conversation and record them with rationale, alternatives, and outcome tracking" names the domain plus several concrete actions (detect, record, rationale, alternatives, outcome tracking), but stops short of the comprehensive coverage of a 5.

4 / 5

Completeness

It clearly states what the skill does, but there is no "Use when..." clause or equivalent trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

The description relies on the domain term "decisions" but lacks the natural phrases users actually say (e.g. "we decided", "going with", "record this decision"), so it sits just above the no-keywords floor.

2 / 5

Distinctiveness Conflict Risk

"Detect decisions in conversation and record them" carves a clear niche with minimal conflict risk, though it has slight overlap with general note-taking or commitment-tracking skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
nearai/ironclaw
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.