CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agently-triggerflow

Use when developer-owned execution needs inspectable branching, concurrency, joins, waits, approval, retry, runtime streams, pause/resume, recovery, or mixed sync/async orchestration. Use agently-stage instead when a provider-owned sync wrapper only bridges an async SDK.

Quality

79%

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 ./skills/agently-triggerflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

An exemplary lean orchestration skill: dense prescriptive rules, concrete API guidance, embedded validation barriers, and a verified one-level-deep reference structure. The main improvements are marginal — relocating the version-check protocol and adding one inline end-to-end example.

Suggestions

Move the 'First use: read-only version check' protocol into a reference file (or a shared package-level location) and keep a one-line pointer in SKILL.md to reclaim ~20 lines of core-skill token budget.

Add a minimal end-to-end inline example (flow definition with a when-handler, an emit, and a pause_for/resume) so the common case is copy-paste ready without opening references/overview.md.

DimensionReasoningScore

Conciseness

The body is dense and telegraphic with zero filler and assumes Claude's competence ("Graph adjacency proves activation, not value transfer"), but the ~20-line 'First use: read-only version check' protocol is inline package policy unrelated to the core orchestration guidance and could be trimmed or moved to a reference file, keeping it below anchor 5.

4 / 5

Actionability

Concrete API calls appear throughout (`flow.create_execution(auto_close=False)`, `pause_for(..., resume_to=...)`, `emit_nowait(...)`, `batch(..., concurrency=N)`) plus an executable import snippet and an explicit anti-patterns list; the gap is that no end-to-end handler example is shown inline (examples are delegated to references/overview.md), so it is 'mostly executable' rather than fully copy-paste ready.

4 / 5

Workflow Clarity

'Topology First' establishes an explicit before-implementation mapping step and validation checkpoints are embedded ("a later model request ... must start after a visible join and validation barrier", "verify external refs, versions, leases, and fence tokens before readiness", "reconcile provisional items against final validated output"), but the guidance is organized by concern rather than as an explicit ordered procedure with feedback loops, which anchor 5 requires.

4 / 5

Progressive Disclosure

The 'Read by Need' section maps each topic to a real reference file — all five references/*.md files exist, are one level deep, and each bullet states exactly what it covers — and cross-skill pointers (../agently-agentic-design, ../agently) are clearly attributed, matching anchor 5's well-signaled one-level-deep navigation.

5 / 5

Total

17

/

20

Passed

Description

70%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 highly distinctive, trigger-focused description with explicit boundary guidance against a sibling skill. Its main weakness is that it never states what the skill does — the capability list implies it, but the 'what' is only weakly implied while the 'when' is fully explicit.

Suggestions

Add a leading 'what' clause stating what the skill provides, e.g. 'Builds inspectable multi-stage workflows with branching, joins, waits, and recovery' before the 'Use when' clause, so completeness reaches both poles explicitly.

Add one or two common user phrasings (e.g. 'workflow orchestration', 'pipeline', 'fan-out') to the trigger list to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description enumerates nine concrete capability areas ("inspectable branching, concurrency, joins, waits, approval, retry, runtime streams, pause/resume, recovery, or mixed sync/async orchestration") rather than vague language, but all are phrased as trigger conditions — the actions the skill actually performs are never stated, which keeps it below anchor 5.

4 / 5

Completeness

The "when" is explicit and rich ("Use when developer-owned execution needs...") and even includes a redirect boundary ("Use agently-stage instead when..."), but the "what" — what the skill actually does or provides — is never explicitly stated and is only implied by the capability list, matching anchor 3's weakly-implied pole rather than anchor 4's both-present.

3 / 5

Trigger Term Quality

Good coverage of natural developer terms ("branching", "concurrency", "joins", "retry", "pause/resume", "recovery", "sync/async"), though common phrasings a user might say such as "workflow", "pipeline", or "orchestration" as trigger words are missing, so it falls short of anchor 5's synonym breadth.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (developer-owned multi-stage execution) and explicitly disambiguates against the sibling skill ("Use agently-stage instead when a provider-owned sync wrapper only bridges an async SDK"), giving minimal conflict risk — a direct match for anchor 5.

5 / 5

Total

16

/

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

AgentEra/Agently-Skills

Path

skills/agently-triggerflow/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.