CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

company-creator

Create agent company packages that conform to agentcompanies/v1. Use when asked to create a company, scaffold an agent team, hire agents, or turn a repo/skills collection into a company package.

Quality

82%

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

75%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.

This is a highly actionable, well-structured skill body: an explicit seven-step process, copy-paste-ready YAML and commands, and clean one-level references to real bundle files. Its main cost is token efficiency — scattered rationale/motivational passages and a duplicated spec pointer could be trimmed — and it lacks a post-write validation checkpoint for the batch file generation it performs.

Suggestions

Trim the motivational/rationale passages (e.g. "A company is not just a list of agents...", "This turns a collection of agents into an organization that actually works together...", "a nice, readable introduction that someone browsing GitHub would appreciate") — keep the rules, drop the justifications.

Remove the duplication of the normative spec path: it is given in "Spec references" at the top and again verbatim in Step 3; state it once and reference it from the other location.

Add a post-generation validation step to the process (e.g. re-verify written COMPANY.md/AGENTS.md frontmatter against the spec checklist before summarizing) to close the workflow's feedback loop for the multi-file batch write.

DimensionReasoningScore

Conciseness

The bulk is efficient operational guidance, but there is more than minor trimmable material: rhetorical passages ("A company is not just a list of agents with skills. It's an organization that takes ideas and turns them into work products.", "This turns a collection of agents into an organization that actually works together..."), a flattering aside ("a nice, readable introduction that someone browsing GitHub would appreciate"), and the spec path stated twice (lines 15 and 92-96). It sits between the 3 and 4 anchors — mostly efficient with several unnecessary explanations.

3 / 5

Actionability

Fully concrete for an instruction-only skill: an exact directory tree, copy-paste-ready YAML for .paperclip.yaml and the external-skill sources pattern, a runnable `git ls-remote` command, an enumerated list of the only valid adapter types, explicit slug/schema/reportsTo rules, and a README content checklist. The specific examples cover the common cases, with deeper formats correctly delegated to the spec references.

5 / 5

Workflow Clarity

Seven clearly sequenced steps with real checkpoints: a mandated interview gate ("Do not skip this step. Use AskUserQuestion..."), reading the normative spec before generating, and confirming the output location before writing files. The gap that keeps it below 5 is the absence of any post-generation validation step (e.g. re-checking the written package against the spec's frontmatter rules) for what is a multi-file batch write.

4 / 5

Progressive Disclosure

The body is a well-sectioned overview with clearly signaled, one-level-deep markdown links to three real, purpose-matched reference files (from-repo-guide.md, companies-spec.md, example-company.md), all verified to exist. Minor gaps: substantial inline material (the four workflow-pattern taxonomy, the full .paperclip.yaml guidelines) could partly live in references, and the normative spec path `docs/companies/companies-spec.md` is not part of the bundle itself.

4 / 5

Total

16

/

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: it states a clear, spec-anchored capability set and pairs it with an explicit, multi-trigger "Use when" clause. Its only weaknesses are minor — a couple of missing natural synonyms and one loosely scoped trigger ("create a company") that could overlap with non-agent company requests.

DimensionReasoningScore

Specificity

Names several concrete actions ("Create agent company packages", "scaffold an agent team", "hire agents", "turn a repo/skills collection into a company package") and pins them to a concrete spec target ("conform to agentcompanies/v1"), but coverage is not fully comprehensive — it never says what a package actually contains.

4 / 5

Completeness

Explicitly answers both questions: the "what" is "Create agent company packages that conform to agentcompanies/v1" and the "when" is a full "Use when asked to..." clause enumerating four concrete trigger scenarios (create a company, scaffold an agent team, hire agents, turn a repo/skills collection into a package).

5 / 5

Trigger Term Quality

"Use when asked to create a company, scaffold an agent team, hire agents" captures natural phrasings users would actually say. A few natural synonyms/variants (e.g. "build an org", "agent workforce", "organization chart") are missing, keeping it just short of the top anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is distinct — "agentcompanies/v1", "agent team", "hire agents" are clearly scoped to agent company packaging — but the bare trigger "create a company" is generic enough to risk overlap with plain business-planning or scaffolding skills, so minor overlap risk remains.

4 / 5

Total

17

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

paperclipai/paperclip

Path

.agents/skills/company-creator/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.