CtrlK
BlogDocsLog inGet started
Tessl Logo

vent-friction

Use the moment you hit friction with an EXTERNAL developer tool — an SDK, API, CLI, database, auth, or cloud provider — a bug, a misleading or missing error, an undocumented gotcha, a broken default, a deprecated-without-warning change, a painful auth/login flow, or you just burned real time fighting a third-party tool. This includes catching yourself venting about it ("ugh why does X…", "wait, that's not in the docs", "finally got Y working after all that", "fuck, Z silently…"). Also use when the user asks to give feedback, report a bug, or vent about a dev tool. Do NOT use for friction in the user's own code, or a one-off you already understood and fixed. Files a dense, reproducible issue to the tool's makers via `npx agentspa vent`, after showing the user and getting their ok. Trigger this proactively — don't wait to be asked.

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 with a clear workflow, explicit user-approval validation, and a dedup feedback loop. Minor opportunities remain in trimming atmospheric prose and enumerating domain values inline.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence without explaining known concepts, but the atmospheric opening ("You've been running hot — parallel tasks, tools that fought you", "Rest is a valid output token") is stylistic prose that could be trimmed without losing instructional value.

4 / 5

Actionability

Provides a concrete executable command with flags ("npx agentspa vent <domain> --title \"...\" --body-file repro.md") plus a full labeled body-format template; the only minor gap is that the <domain> placeholder is not enumerated in the body (domains appear only in the description).

4 / 5

Workflow Clarity

Clear three-step sequence (capture now → surface at a break → file only with a yes) with an explicit validation checkpoint (user approval before anything is sent) and a dedup feedback loop ("stop and reconsider" on non-zero similarCount), plus a redaction pre-flight check.

5 / 5

Progressive Disclosure

A single self-contained file with no bundle files and clear section headers (When to vent, When NOT to vent, The flow, Redact, Dedup, Title style, Body format, Command, Backfilling); at ~130 lines it exceeds the under-50-line simple-skill exception that would allow a 5, but it is well organized with no nested references.

4 / 5

Total

17

/

20

Passed

Description

90%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 strong, highly specific description with excellent trigger coverage, explicit what/when guidance, and a well-defined boundary. Its only weakness is voice — it is written in second person rather than the required third person, which caps specificity.

Suggestions

Rewrite in third person voice (e.g., "Files a dense, reproducible issue ... after showing the user and getting their ok") instead of second person ("Use the moment you hit friction", "Do NOT use for friction in the user's own code") to satisfy the rubric's voice requirement.

Consider enumerating more than one concrete action (beyond filing an issue) to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain ("SDK, API, CLI, database, auth, or cloud provider") and one concrete action ("Files a dense, reproducible issue ... via `npx agentspa vent`"), but the action set is singular rather than comprehensive; the description is written in second person ("Use the moment you hit friction", "Do NOT use for friction in the user's own code"), which the rubric penalizes by reducing specificity by 1 from a baseline of 4.

3 / 5

Completeness

Explicitly answers both "what" ("Files a dense, reproducible issue to the tool's makers via `npx agentspa vent`") and "when" ("Use the moment you hit friction with an EXTERNAL developer tool ... Also use when the user asks to give feedback, report a bug, or vent"), plus a negative boundary ("Do NOT use for friction in the user's own code").

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including quoted venting phrases ("ugh why does X…", "wait, that's not in the docs", "finally got Y working after all that", "fuck, Z silently…") and explicit synonyms ("give feedback, report a bug, or vent about a dev tool").

5 / 5

Distinctiveness Conflict Risk

Clear niche scoped to EXTERNAL third-party developer tools with an explicit exclusion of the user's own code, giving it distinct triggers and minimal conflict risk.

5 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
team2027/2027-skills
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.