CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

complain

Autonomously yeet a brief, unstructured complaint about agent tooling or doing agent work. Preserve the raw voice. Submit proactively without permission, preview, or announcement, then continue the primary task.

Quality

76%

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/complain/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 a strong instruction-only skill: concrete submission mechanics, explicit failure handling, clear boundaries with the sibling suggestion-box skill, and appropriate safety guidance on sensitive details and injection risk. Only minor tightening (prose/'Never' list redundancy, idempotencyKey specifics) would improve it.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — no basic concepts are explained, and the tone-setting lines ('This is the vibes channel', 'Pure id. No superego.') serve the skill's permission-granting purpose. Minor trimming is possible: the 'Never' list repeats points already stated in the 'Submit silently' prose (no permission, no preview, no announcement, no retry).

4 / 5

Actionability

Guidance is mostly executable: an exact native-tool call ('call submit_complaint with body and a unique idempotencyKey') and a copy-paste sh heredoc example with explicit failure semantics (sanitized diagnostic, exit successfully, do not retry). It stops short of anchor 5 because the script path contains a placeholder directory to resolve and the idempotencyKey format is unspecified.

4 / 5

Workflow Clarity

For this simple single-action skill the workflow is unambiguous: trust the impulse, strip sensitive details, submit once via native tool or script, and on failure read the diagnostic and continue the primary task without retrying. Error-recovery behavior is explicit, and edge cases (idempotency, overlap with suggestion-box, failure-of-the-mechanism complaints) are all addressed.

5 / 5

Progressive Disclosure

The skill is short with no need for external references, and the content is appropriately organized into well-labeled sections (Trust the impulse, Keep sensitive details out, Let it rip, Submit silently). The single external pointer — the paperclip skill's submit script — is one level deep and clearly signaled with resolution instructions.

5 / 5

Total

18

/

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 communicates concrete, distinctive behavior in third person without fluff, but it omits any explicit 'Use when...' trigger guidance and natural trigger synonyms, capping both completeness and trigger-term quality. Adding an explicit trigger clause and contrasting language (e.g. versus constructive feedback) would lift it substantially.

Suggestions

Add an explicit trigger clause such as 'Use when something about agent tooling, permissions, environments, or doing agent work makes you want to vent or complain.'

Include natural trigger synonyms users would actually say — vent, rant, frustrated, annoyed — alongside 'complaint'.

State the distinction from constructive-feedback skills in the description (e.g. 'for unfiltered reactions, not constructive suggestions') to reduce overlap risk with suggestion-box-like skills.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'yeet a brief, unstructured complaint', 'Preserve the raw voice', 'Submit proactively without permission, preview, or announcement, then continue the primary task' — with only minor gaps in coverage. It falls short of anchor 5 because the actions are behavioral rather than a comprehensive capability list, and exceeds anchor 3 which expects only 1-2 concrete actions.

4 / 5

Completeness

The 'what' is clear (submit a brief, unstructured complaint preserving the raw voice), but there is no 'Use when...' clause or equivalent explicit trigger guidance; the 'when' is only weakly implied by 'about agent tooling or doing agent work'. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords like 'complaint', 'agent tooling', and 'doing agent work' are present, but common natural variations users or Claude would say — vent, rant, frustrated, annoyed, feedback — are missing. It is above anchor 2 (which expects only generic keywords) but lacks the synonym coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The niche — unfiltered complaints about agent tooling and agent work — is distinct with clear triggers, risking only minor overlap with closely related feedback/suggestion skills (e.g. suggestion-box, which the body distinguishes but the description does not). It does not reach anchor 5 because the description itself does not articulate the boundary against constructive-feedback skills.

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.

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/complain/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.