CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

team-builder-packaging

Use when generating or auditing a multi-role agent team package with orchestrator, workers, handoffs, Memory Ticket outputs, and runtime adapters (PM Soul, Memory Curator, Policy Gate, eval and QA are OS-resident).

Quality

71%

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/team-builder-packaging/SKILL.md

The canonical home for this skill is team-builder-packaging in agentlas-ai/Agentlas-OS

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 compact, well-sequenced packaging procedure with a real verification feedback loop and concrete output artifacts. Its weaknesses are dangling references to files not present in the bundle and missing examples for the core generated artifacts (agent.md, handoff contracts), which leave several steps executable only in intent.

Suggestions

Ship the referenced files in the bundle or make their location unambiguous: `scripts/verify-team-package.sh` and `contracts/builder-interview-research-gate.md` are invoked by name but no scripts/ or contracts/ directory exists, so step 2 and step 11 cannot actually be executed.

Add a minimal inline example of the artifacts the procedure generates — one agent.md skeleton and one handoff/return contract — since steps 4, 6, and 8 currently instruct without showing shape.

Fix the step numbering (1-10 with an inserted '9b' and a duplicated 9) and consider an early checkpoint after the interview/research gate so mis-shaped rosters are caught before adapters and commands are emitted.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: a numbered procedure, specific file paths, and a JSON snippet with no concept teaching. Minor over-explanation remains, e.g., the motivational aside in step 9b ('a package that omits it is published, charged for as a team, and can never be called').

4 / 5

Actionability

There is concrete guidance (docs file list, manifest.json example, `scripts/verify-team-package.sh <package-root>`), but the referenced script and `contracts/builder-interview-research-gate.md` do not exist in the skill bundle, and core artifacts like agent.md or handoff/return contracts get no example — more than the minor gaps of anchor 4.

3 / 5

Workflow Clarity

The 11-step procedure is clearly sequenced with an explicit terminal validation and remediation loop ('If it fails, do not hand off a result; correct the package by adding an orchestrator/HQ ... or by collapsing it'). The out-of-sequence '9b' numbering and validation only at the end keep it below anchor 5.

4 / 5

Progressive Disclosure

The body has two clean sections (Procedure, Output) and stays short, but its references (`contracts/builder-interview-research-gate.md`, `scripts/verify-team-package.sh`) point to files absent from the bundle — no references/, scripts/, or assets/ directories exist — leaving navigation dangling, which anchor 4's 'references mostly clear' does not cover.

3 / 5

Total

14

/

20

Passed

Description

66%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 well-formed trigger-style description with an explicit 'Use when' clause, a clearly identified niche, and low conflict risk. Its main weaknesses are generic action verbs and heavy internal jargon that limits natural trigger-term coverage.

Suggestions

Replace the generic verbs 'generating or auditing' with more specific actions (e.g., 'Builds the roster, handoff contracts, manifest, and runtime adapters for a multi-role agent team package, and audits existing packages').

Add natural trigger variations users would actually say, such as 'build a team of agents', 'agent roster', or 'package a multi-agent team', and move OS-resident component jargon (PM Soul, Memory Curator, Policy Gate) out of the description.

DimensionReasoningScore

Specificity

The description offers two generic actions ("generating or auditing") plus a domain component list ("orchestrator, workers, handoffs, Memory Ticket outputs, and runtime adapters"), which names the domain with 1-2 concrete actions but does not enumerate several specific actions as anchor 4 requires.

3 / 5

Completeness

Both elements are explicitly present and fused in one clause: the what ("generating or auditing a multi-role agent team package") and the when ("Use when..."). It falls short of anchor 5 because the when lacks concrete alternative trigger phrases, and exceeds anchor 3 because neither element is missing or merely implied.

4 / 5

Trigger Term Quality

Some relevant keywords like "agent team package", "orchestrator", and "workers" match what a user in this domain would say, but internal jargon ("PM Soul", "Memory Curator", "Policy Gate", "Memory Ticket") is not natural user language and common variations such as "build a team of agents" are missing.

3 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (multi-role agent team packaging with OS-resident gates) with distinct trigger terms; overlap risk with any other skill is minimal.

5 / 5

Total

15

/

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

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/verify-team-package.sh)

Warning

Total

15

/

16

Passed

Repository

agentlas-ai/Agentlas-OS

Path

.agents/skills/team-builder-packaging/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.