CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

suggestion-box

Quietly suggest a concrete improvement after observing material, generalizable friction in agent work. Submit proactively without permission, preview, or announcement, then continue the primary task.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 a tightly written, highly actionable single-file skill: concrete submission criteria, a copy-paste command, an explicit failure policy, and clean section structure. Only minor redundancy between the "Never" list and adjacent prose keeps it from full token efficiency.

DimensionReasoningScore

Conciseness

The body is dense and rule-driven with no explanations of concepts Claude already knows — every section (criteria, prohibited content, failure policy) is load-bearing. Minor trimming opportunities exist, e.g., the "Never" list repeats the announcement/truthfulness rules already stated in the preceding paragraph, which keeps it just below the lean-efficiency anchor of 5.

4 / 5

Actionability

Guidance is fully concrete: exact submission criteria, explicit prohibited-content lists, a copy-paste heredoc command example with resolution instructions for the script path, the native-tool signature (submit_suggestion with body and a unique idempotencyKey), and explicit failure handling — matching the fully executable, common-cases-covered anchor.

5 / 5

Workflow Clarity

As a single-action skill the sequence is unambiguous: check the when-to-submit criteria checklist, compose per the format rules, submit via one of two concrete mechanisms, and follow the explicit failure policy (sanitized diagnostic, exit success, never retry). This is not a destructive or batch operation, so no validation cap applies, and the simple-skill exception holds.

5 / 5

Progressive Disclosure

The skill is a single well-organized file with clearly labeled sections and no bundle files to split; the only referenced script is external (resolved from the installed paperclip skill directory), clearly signaled, and exactly one level deep with resolution instructions — matching the clear-overview, easy-navigation anchor.

5 / 5

Total

19

/

20

Passed

Description

67%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 and concretely states both what the skill does and when to use it, with a distinctive silent-submission identity. Its main weakness is moderate natural trigger keyword coverage — synonyms like "feedback" or "report" that users would actually say are absent.

Suggestions

Broaden natural trigger keywords with synonyms such as "feedback", "report an issue", or "improvement idea" so the description matches phrasings users actually say.

Consider an explicit "Use when..." clause with concrete friction examples (e.g., inconsistent tool behavior, unnecessary approval loops) to sharpen the trigger guidance.

DimensionReasoningScore

Specificity

Lists several concrete actions — "suggest a concrete improvement", "Submit proactively without permission, preview, or announcement", "continue the primary task" — with only minor coverage gaps, matching the anchor for several specific actions rather than the comprehensive coverage of a 5.

4 / 5

Completeness

The 'what' is clear (quietly suggest and submit a concrete improvement) and the 'when' is explicit ("after observing material, generalizable friction in agent work"), but it lacks the stronger 'Use when...' phrasing with concrete trigger phrases that would merit a 5; it is well above a merely implied 'when' (3).

4 / 5

Trigger Term Quality

Relevant keywords like "suggest", "improvement", "friction", and "agent work" are present, but common natural variations a user might say ("feedback", "report an issue", "complaint") are missing, which fits the 'some relevant keywords but missing variations' anchor rather than the good coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

The silent, constructive-improvement niche about agent infrastructure is mostly distinct — the body even distinguishes it from the sibling 'complain' skill — with only minor overlap risk against general feedback/complaint skills, matching anchor 4 rather than the minimal-conflict clarity of a 5.

4 / 5

Total

15

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

paperclipai/paperclip

Path

skills/suggestion-box/SKILL.md

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.