CtrlK
BlogDocsLog inGet started
Tessl Logo

paperclip-task-bridge

Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.

62

Quality

73%

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 ./packages/adapters/hermes/skills/paperclip-task-bridge/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 tight, domain-specific skill with strong executable guidance and a sensible implicit workflow, but its single external reference (paperclip-task.mjs) is missing from the bundle and the key-creation example relies on two undocumented environment variables. Fixing those two gaps would move it close to top marks across the board.

Suggestions

Ship paperclip-task.mjs in the skill bundle (or fix the path so the reference in the Helper section resolves), since every command in the skill depends on it.

Document $BOARD_API_KEY and $HERMES_AGENT_ID in the Required Environment section (or note they come from the board-authenticated Paperclip session), as the key-creation curl example uses both without defining them.

Add a short error-recovery note for mutating requests — e.g., what a scope-boundary rejection from parentIssueId/projectId looks like and to re-check the bridge key's boundary before retrying.

DimensionReasoningScore

Conciseness

The body is lean and almost entirely Paperclip-specific knowledge Claude would not already have (scoped key creation, env vars, helper flags), with every section earning its tokens. A few lines could be trimmed — "Never print or paste API keys" and "Use comments for durable progress" state things that are obvious or chatty — keeping it just below the anchor-5 'every token earns its place' bar.

4 / 5

Actionability

Concrete, copy-paste-ready helper commands cover the common cases (list, create, comment, update-status, multiline bodies via --description-file/--body-file, --unassigned), matching the anchor-4 'mostly executable with minor gaps' example. The gap: the key-creation curl uses "$BOARD_API_KEY" and "$HERMES_AGENT_ID", neither documented in Required Environment, and the commands depend on ./paperclip-task.mjs which is not present in the provided bundle.

4 / 5

Workflow Clarity

The document's section order encodes a clear sequence (configure env → create scoped bridge key once → run helper → follow workflow expectations), and 'Use list-assigned before creating duplicate work when the user asks about current Paperclip assignments' is an explicit pre-flight checkpoint. It falls short of anchor 5 because there is no error-recovery guidance (e.g., what to do when a mutating request fails or the key's scope boundary rejects a parent/project id), and it stays above 3 because the operations are not destructive/batch and a real checkpoint exists.

4 / 5

Progressive Disclosure

Sections are well organized and the only reference (the helper script) is signaled at one level deep, but verification shows ./paperclip-task.mjs is not present in the bundle — there are no references/, scripts/, or assets/ directories and no script at the skill root — so the central 'Helper' section points at an unresolvable path. The body is also ~77 lines, so the under-50-lines simple-skill exception does not apply; structure is good but navigation does not fully resolve.

3 / 5

Total

15

/

20

Passed

Description

75%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 crisp, third-person, highly specific description with excellent distinctiveness, held back only by the absence of any 'when to use this' trigger clause. Adding one sentence of explicit trigger guidance and a few natural synonyms would bring it to the top anchor across all dimensions.

Suggestions

Add an explicit trigger clause, e.g., "Use when a Hermes-originated request needs to create, comment on, update, or list Paperclip tasks" — completeness is capped at 3 without it.

Include natural synonyms users say, such as "Paperclip issues" or "PAP-" ids, alongside "tasks" to broaden trigger coverage.

DimensionReasoningScore

Specificity

"Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials" names the domain plus four concrete actions and the mechanism (scoped API credentials), comprehensively covering the skill's operation surface. Not 4: this is full coverage of what the helper does, not 'several actions with minor gaps'.

5 / 5

Completeness

The 'what' is clear and concrete (create/comment/update/list Paperclip tasks from Hermes), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description. Per the judging guidelines, a missing explicit trigger caps completeness at 3 even with a crisp 'what'.

3 / 5

Trigger Term Quality

Good natural keyword coverage — "Paperclip tasks", "create", "comment on", "update", "list", "Hermes" — phrases a user would plausibly say. Not 5: common synonyms and identifiers users actually use are missing, e.g., "issues"/"PAP-" ids (the body itself comments on issues like PAP-123) and direction words like "sync" or "bridge".

4 / 5

Distinctiveness Conflict Risk

The Hermes→Paperclip pairing with task_bridge-scoped credentials carves out a clear niche with essentially no overlap risk against generic task skills, and even disambiguates direction. Not 4: there is no plausible closely-related skill it would wrongly trigger — the specific product names and scope kind make confusion minimal.

5 / 5

Total

17

/

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
paperclipai/paperclip
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.