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.

61

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/address-feedback/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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, highly actionable policy skill with explicit gates, verification steps, and copy-paste reply formats. Its weaknesses are redundancy (the fix-altitude guidance appears twice) and the absence of any progressive disclosure: a long body inlines Slack-interop and sibling-skill rules that belong in separate files.

Suggestions

Merge the duplicated 'Choose the fix altitude' and 'Fix-altitude gate' sections into a single gate, cutting roughly 16 repeated lines and removing the flow ambiguity between them.

Trim the anecdotal repeat-report narratives in step 2 to the actionable rule ('search at least three months back, in the reporter's words and yours, across Sentry/Analytics/PR titles'), since the stories exist only to motivate that instruction.

Move the address-feedback-with-replies Slack status-state rules into a reference file (or into that sibling skill) and keep a short one-level pointer in SKILL.md, splitting the ~290-line body for progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense, imperative policy with no basic-concept padding, but the 'Choose the fix altitude' and 'Fix-altitude gate' sections near-duplicate each other, and the anecdotal repeat-report stories ('filed almost word-for-word 29 days apart', 'reported fifteen times by nine people') are narrative padding that could be cut to a single rule.

3 / 5

Actionability

Concrete guidance throughout: a source-to-reader table, exact commands ('gh issue view', 'list-error-issues', 'get-error-issue'), exact status labels, and a copy-paste reply template with verbatim phrases like 'Expected live by EOD.' The residual abstraction ('name the smallest invariant that explains the report') is inherent judgment guidance rather than executable detail, keeping it below a 5.

4 / 5

Workflow Clarity

Steps 1-8 are clearly sequenced with explicit validation gates (clarification gate, fix-altitude gate, 'Verify before fixing', step 8 verification) and regression-check feedback loops. The literal duplication of the altitude guidance between two headings slightly muddies the flow, and the gates interleave with the numbered steps, so it sits just below the 5 anchor.

4 / 5

Progressive Disclosure

No bundle files exist and headers are well-organized, but the ~290-line body inlines substantial content that belongs in the referenced sibling skills or reference files - notably the ~25-line 'address-feedback-with-replies' interop rules and the detailed Slack status-state rules - so it matches 'some structure but content that should be separate is inline'.

3 / 5

Total

14

/

20

Passed

Description

83%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, concrete about sources and outcome categories, with an explicit 'Use when...' trigger clause covering both feedback-addressing and workflow-investigation phrasings. The only gaps are missing action verbs for the fix/verify half of the skill and a few common synonyms like 'bug report'.

DimensionReasoningScore

Specificity

'Triage feedback from docs, issues, Slack threads, or pasted notes into verified bugs, UX proposals, unclear questions, and skipped noise' names several concrete actions and four source types with four outcome categories, but it omits the fix-and-verify actions the skill actually performs - a minor coverage gap that fits anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

It clearly and explicitly answers both: the 'what' ('triage feedback... into verified bugs, UX proposals, unclear questions, and skipped noise') and the 'when' ('Use when a user asks you to address product feedback or investigate a reported workflow') with concrete trigger phrases in third person - a direct match for anchor 5.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ('address product feedback', 'investigate a reported workflow', 'issues', 'Slack threads', 'pasted notes'), but common synonyms users would say - 'bug report', 'feature request', 'suggestion' - are missing, matching anchor 4's 'a few natural terms missing' rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The feedback-triage niche with Slack/docs/issue sources and its 'address product feedback' trigger are clearly distinct, but it slightly overlaps adjacent issue-handling and code-review skills the body itself lists as related ('github:gh-address-comments'), fitting anchor 4's 'minor overlap risk with closely related skills' rather than the minimal-conflict anchor 5.

4 / 5

Total

17

/

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.

Validation — 13 / 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.