CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

session-agent-builder

Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit terminal and automation runs.

Quality

67%

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 ./codex/plugins/agentlas-core-engine-meta-agent/skills/session-agent-builder/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.

The skill is a lean, well-sectioned instruction document with a clear sequenced workflow and genuine safety/validation checkpoints. Its main weaknesses are deferred execution detail — the canonical route files it points to are not in the bundle, and "verify gates" is never concretized — which hurts both actionability and progressive disclosure.

Suggestions

Ship the canonical route files (e.g., place modes/session-agent-builder.md under references/) or inline the essential steps of the scaffold/registration process so the skill is executable standalone.

Concretize the validation boundary: name the actual checks or commands behind "verify gates" and "local validation boundary" (e.g., what to run and what pass looks like) instead of naming them abstractly.

Expand "route it through the existing package scaffold, complete, local registration, and verify gates" into its constituent sub-steps, since this is the skill's core deliverable and is currently the vaguest instruction.

DimensionReasoningScore

Conciseness

The body is an efficient instruction-only document with no explanation of concepts Claude already knows; e.g., the safety section is a terse bullet list ("Never carry raw transcripts, hidden prompts, credentials, tokens..."). Minor tightening is possible — "The important distinction is between an interactive host and the deterministic terminal utility" and "The deterministic runner remains available for explicit exports" restate constraints already implied elsewhere — so it is not level 5, but it is well above the mostly-efficient level 3.

4 / 5

Actionability

Some guidance is concrete (defaults like `AGENTLAS_AGENT_HOME` or `~/.agentlas/agents`, the command `session preview|merge|ir|compile --input <session.jsonl>`), but the core execution is deferred: "route it through the existing package scaffold, complete, local registration, and verify gates" and the pointer to `modes/session-agent-builder.md` leave the actual write/registration steps unspecified, and those referenced files are absent from the bundle. Not level 2 — there is substantial specific guidance (report contents, IF/THEN/BECAUSE/AVOID/INSTEAD rules, destination rules) — but key executable detail is missing, which blocks level 4.

3 / 5

Workflow Clarity

The interactive route is a clear 5-step sequence with explicit checkpoints: owner review before any write ("Show the report for owner review... editing regenerates the report before any package write"), "never overwrite an existing child", and "verify gates" in step 5. Not level 5 because the validation itself ("verify gates", "local validation boundary") is named but its concrete checks are unspecified; comfortably above level 3, where checkpoints would be merely implicit.

4 / 5

Progressive Disclosure

The body is short (~59 lines) with well-labeled sections, but it declares `modes/session-agent-builder.md` and `agents/40-session-agent-builder/agent.md` as "the canonical route" and neither file exists in the bundle (no references/, scripts/, or assets/ directories). The primary reference is therefore dangling, leaving navigation incomplete — better than level 2 (structure exists and references are clearly signaled) but the missing canonical files are more than the minor organization gaps of level 4.

3 / 5

Total

14

/

20

Passed

Description

53%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 states a clear, distinct capability in third person without fluff, but it lacks any explicit "when to use" trigger guidance and misses the natural phrases users would say to invoke it. Coverage of the skill's actual actions is narrow — only two actions are named.

Suggestions

Add an explicit trigger clause, e.g., "Use when the owner asks to turn this session or conversation into a reusable agent, or supplies a session JSON/JSONL export for headless processing."

Include natural trigger phrases users would say, such as "build an agent from this session", "save this conversation as an agent", or "agentify this chat".

Name one or two more concrete capabilities (generalized session report, redaction of private identifiers, local validation) to broaden action coverage.

DimensionReasoningScore

Specificity

"Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent" and "accept JSON or JSONL only for explicit terminal and automation runs" name the domain plus two concrete actions, but coverage is not comprehensive — report generation, redaction, validation, and registration are all unstated. It is above level 2 (actions are specific, not generic) but below level 4, which requires several specific actions with only minor gaps.

3 / 5

Completeness

The "what" is clear (convert the current conversation into an owner-reviewed reusable agent; accept JSON/JSONL for terminal runs), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Level 4 requires both what and when with the when explicit; level 2 would require a vague what, which this is not.

3 / 5

Trigger Term Quality

Terms like "interactive conversation", "reusable agent", "JSON", "JSONL", and "terminal" are relevant, but the natural phrases a user would actually say (e.g., "build an agent from this session", "save this conversation as an agent", "session export") are missing. Not level 2 since the keywords are domain-relevant rather than generic; not level 4 since common variations and synonyms are largely absent.

3 / 5

Distinctiveness Conflict Risk

The niche is fairly distinct — "owner-reviewed reusable Agentlas agent" and the JSON/JSONL terminal boundary are specific to this skill, with only minor overlap risk against generic agent-building or session-export skills. Not level 5 because without explicit trigger phrases, related agent-creation skills could still collide on generic requests.

4 / 5

Total

13

/

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

agentlas-ai/Agentlas-OS

Path

codex/plugins/agentlas-core-engine-meta-agent/skills/session-agent-builder/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.