CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-agent-adapter

Create or modify Paperclip agent adapters across server, UI, and CLI surfaces. Use when adding support for a new CLI agent, API agent, custom process, or adapter package.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable, well-sequenced guide for a genuinely complex multi-surface task, with strong validation and error-recovery guidance. Its main weakness is monolithic structure — reference-grade tables and patterns are inlined in one long file with no progressive disclosure to bundle files.

Suggestions

Move the TranscriptEntry kinds table (§9), the server-utils helper table (§6), and the injected env-var table (§3.3) into a references/ file (e.g. references/types-and-helpers.md) and link to it from SKILL.md to reduce inline bulk.

Extract the skills-injection patterns (§7) into their own reference file, keeping only the constraint statement and the four-option decision summary in SKILL.md.

Trim duplicated session-management content between §3.3 (execute step 3/8) and §5, merging the retry pattern into a single location.

DimensionReasoningScore

Conciseness

The body is dense with genuinely non-obvious domain knowledge (interfaces, env vars, registries, codecs) and avoids explaining concepts Claude already knows. It earns 4 rather than 5 due to repetition (session handling in §3.3 and §5, lengthy skills-injection prose in §7) and meta-commentary like "One concrete anti-pattern is worth more than three paragraphs of description".

4 / 5

Actionability

Provides complete interface definitions, a copy-ready package.json, registration snippets, and helper/env-var tables. Several blocks are skeleton-style with placeholder comments (parse-stdout, build-config, sessionCodec), which are appropriate templates but not fully executable, so it falls short of the 5 anchor.

4 / 5

Workflow Clarity

Clear step-by-step sequence (package → metadata → server → UI → CLI → registration → testing) with explicit validation checkpoints: §10 testing requirements, the §11 checklist, and a concrete error-recovery feedback loop (unknown-session retry with clearSession). This matches the 5 anchor's sequencing plus explicit validation and error recovery.

5 / 5

Progressive Disclosure

Good section structure with numbered, navigable headings, but the skill is a single ~700-line monolithic file with no reference files at all; reference-grade material (TranscriptEntry kinds table, env-var table, server-utils helper table, skills-injection patterns) is inlined. This matches the 3 anchor (structure present, content that should be separate is inline) better than the 2 anchor, since organization itself is solid.

3 / 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.

The description is well-constructed: third-person voice, explicit what-and-when structure, and concrete enumerated trigger cases. Its only weaknesses are slightly generic action verbs and a few missing natural synonyms (agent names, "integrate").

DimensionReasoningScore

Specificity

Lists several concrete actions — "Create or modify", "across server, UI, and CLI surfaces" — and enumerates the adapter kinds ("CLI agent, API agent, custom process, or adapter package"). Falls short of 5 because it doesn't enumerate the constituent actions involved (parsing output, config forms, registry registration).

4 / 5

Completeness

Clearly answers both what ("Create or modify Paperclip agent adapters across server, UI, and CLI surfaces") and when ("Use when adding support for a new CLI agent, API agent, custom process, or adapter package") with concrete trigger phrases. Matches the 5 anchor exactly rather than the 4 anchor, since the when-clause is explicit and specific.

5 / 5

Trigger Term Quality

"Use when adding support for a new CLI agent, API agent, custom process, or adapter package" provides good natural-phrasing coverage. A few natural terms are missing (e.g., "integrate a new agent", specific agent names like Codex or Claude Code), so it doesn't reach comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Anchored on the distinct "Paperclip agent adapters" niche with clear, specific triggers; minimal conflict risk with other skills. Not a 4 because the domain anchor and trigger set leave virtually no overlap with generic skills.

5 / 5

Total

18

/

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

skill_md_line_count

SKILL.md is long (717 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

paperclipai/paperclip

Path

.agents/skills/create-agent-adapter/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.