CtrlK
BlogDocsLog inGet started
Tessl Logo

idea-parking

Park interesting ideas for later consideration, resurface them periodically, and promote to commitments when ready.

56

Quality

63%

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/idea-parking/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 well-structured, concise, and largely actionable with a strong validation checkpoint on the primary parking workflow, but the destructive promote/dismiss paths lack verification steps and a few steps remain slightly abstract.

Suggestions

Add a verification step before destructive overwrites in promote/dismiss (e.g., confirm the file exists via memory_tree/memory_read, then verify the overwrite succeeded) to lift the workflow_clarity cap.

Make 'Find the matching parked idea' concrete by specifying how to locate it (e.g., memory_tree + match on title/slug) so the promote flow is fully executable.

Tighten the redundant user-phrase examples at the top of each section to push conciseness toward 5.

DimensionReasoningScore

Conciseness

The body is lean with concrete tool calls, a compact file template, and no padding of concepts Claude already knows; a few illustrative user-phrase examples could be trimmed, keeping it just below the 'every token earns its place' level 5.

4 / 5

Actionability

Provides concrete, executable guidance — specific memory_write paths, a copy-paste-ready frontmatter template, and exact confirm strings — but a couple of steps like 'Find the matching parked idea' and 'Create a commitment based on the idea content' are slightly abstract, leaving minor gaps.

4 / 5

Workflow Clarity

The parking workflow has an explicit mandatory sequence with a validation checkpoint ('Only then confirm', 'Never say... unless memory_write succeeded'), but the destructive promote/dismiss operations overwrite files with empty content and lack any verification that the file existed or the write succeeded, triggering the destructive-ops cap at 3.

3 / 5

Progressive Disclosure

Content is self-contained in one well-organized file with clear per-task sections and no nested references; at ~70 lines it sits just above the under-50-line simple-skill threshold, so it lands at 'good structure, appropriately placed' rather than a clean 5.

4 / 5

Total

15

/

20

Passed

Description

58%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 concisely states what the skill does with several concrete actions, but omits any explicit 'when to use' trigger guidance, which caps completeness and weakens trigger-term quality.

Suggestions

Add an explicit 'Use when the user wants to defer an idea, says "save for later" / "park this", or wants to revisit shelved ideas' clause to satisfy the completeness 'when' requirement.

Surface natural trigger phrases (e.g., 'save for later', 'backburner', 'shelve this') directly in the description to raise trigger_term_quality.

Mention the full lifecycle (park, list, promote, dismiss) so specificity reflects the skill's complete coverage.

DimensionReasoningScore

Specificity

Names three concrete actions — 'Park interesting ideas', 'resurface them periodically', and 'promote to commitments' — which lists several specific actions with minor gaps in coverage; not a 5 because coverage is not comprehensive (no listing/dismissal actions mentioned).

4 / 5

Completeness

It clearly states what the skill does but contains no 'Use when...' clause, so per the rubric a missing explicit trigger guidance caps completeness at 3; not a 4 because 'when' is only weakly implied rather than stated.

3 / 5

Trigger Term Quality

The description embeds a few natural terms users would say ('park interesting ideas', 'for later consideration') but misses common variations like 'save for later' or 'backburner', matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The 'park / resurface / promote to commitments' framing carves a mostly distinct niche with minor overlap risk against general note-taking or commitment skills; not a 5 because no explicit distinct trigger phrases are given in the description itself.

4 / 5

Total

14

/

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.