CtrlK
BlogDocsLog inGet started
Tessl Logo

address-feedback

Triage feedback from docs, issues, Slack threads, or pasted notes into verified bugs, UX proposals, unclear questions, and skipped noise. Use when a user asks you to address product feedback or investigate a reported workflow.

65

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 workflow with strong sequencing and validation checkpoints. Its main weakness is conciseness: the altitude guidance is duplicated across two sections and the Slack-precedence rules are stated repetitively, inflating the body without adding guidance value.

Suggestions

Collapse the duplicated "Choose the fix altitude" and "Fix-altitude gate" sections into one; the second occurrence is near-verbatim and adds ~25 lines of redundancy.

Tighten the Slack-precedence paragraph in User-Facing Reply: state each rule once (status set, thank-you opening, clarification-only-when-needed, no-technical-details) instead of restating them across multiple sentences.

Consider extracting the long Slack reply-state rules into a one-level-deep reference (e.g. references/slack-replies.md) to keep SKILL.md an overview and improve progressive disclosure.

DimensionReasoningScore

Conciseness

It assumes Claude's competence (no explaining of what Slack or a bug is) and is mostly efficient, but the "Choose the fix altitude" and "Fix-altitude gate" sections repeat the same four bullets nearly verbatim and the Slack-precedence paragraph restates its rules multiple ways, so it could be tightened.

3 / 5

Actionability

It gives concrete, executable guidance — a source/reader table, specific commands ("gh issue view", "gh pr view"), a copy-paste reply-status template, and explicit category definitions — with only minor gaps where guidance rests on judgment (e.g., "fix only the clear bugs you agree with") rather than a runnable procedure.

4 / 5

Workflow Clarity

Steps 1–8 are clearly sequenced with explicit validation checkpoints (verify before fixing, "Verify changed behavior" as step 8), dedicated gates (Clarification gate, Fix-altitude gate), and error-recovery feedback loops (reproduce→fix→re-verify, prior-report branches), matching the top anchor; the batch/reactive operations do have verification, so no cap applies.

5 / 5

Progressive Disclosure

The file is well-organized with clear section headers and navigable structure (Steps, gates, User-Facing Reply, Avoid, Related Skills), and most content is appropriately placed; it is monolithic with no reference files, and a couple of dense inline sections (the Slack reply rules) could be extracted, leaving minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

87%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 description: third-person voice, concrete sources and output categories, and an explicit "Use when" trigger covering both what and when. The only minor gap is that the action collapses to a single triage verb rather than several distinct operations.

DimensionReasoningScore

Specificity

Names the domain ("docs, issues, Slack threads, or pasted notes") and concrete output categories ("verified bugs, UX proposals, unclear questions, and skipped noise"), but the core action is a single verb (triage into categories) rather than several distinct verbs, leaving minor coverage gaps versus the comprehensive multi-action anchor.

4 / 5

Completeness

It explicitly answers both "what" (triage feedback from named sources into four named categories) and "when" ("Use when a user asks you to address product feedback or investigate a reported workflow") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ("address product feedback", "investigate a reported workflow", "Slack threads", "pasted notes") that a user would plausibly say, with good keyword coverage; a few common synonyms (e.g., "bug report", "customer feedback") are missing, so it sits just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (feedback triage with named source types and a specific "address product feedback / investigate a reported workflow" trigger) with minimal overlap risk against other skills, matching the clear-niche anchor.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
BuilderIO/agent-native
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.