CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

maple-agent-tracing-haystack

Trace Haystack agents with Maple: installs a small Haystack tracer that adds OpenTelemetry GenAI attributes to Haystack's own spans, so each conversation is one Maple Agent Session with transcript, model, tokens, cost and tool failures. Triggers on 'trace my haystack agent', 'add Maple to haystack', 'agent sessions for haystack', 'OpenTelemetry for haystack'.

76

Quality

95%

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

96%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 excellent operational guide: fully executable code and commands, a clearly sequenced workflow with explicit validation and recovery loops, and lean domain-specific prose with no padding. The only structural nit is that all reference-grade material (verify checklist, known behaviours) lives inline in one large file rather than being offloaded to bundle files.

DimensionReasoningScore

Conciseness

The body is dense imperative prose with zero concept explanations ('Need >=3.0; guide verified on 3.2', 'Never a per-request UUID, never a process-wide constant') and version numbers only as functional constraints. Every token carries Maple/Haystack-specific operational fact, matching the lean-and-efficient anchor; not 4 since no section is trimmable over-explanation.

5 / 5

Actionability

Fully executable throughout: a verbatim pip install command, a complete copy-paste-ready maple_haystack.py module, init and env-var snippets, a flush pattern, and a verification procedure with fallbacks (no-key handling, 401 region swap, local exporter when Maple is unavailable). Matches the copy-paste-ready anchor covering common cases.

5 / 5

Workflow Clarity

Steps 0-7 are clearly sequenced (Detect, Key/region, Install/init, Session id, Content, Tools/errors, Flush, Verify) with an explicit Step 7 validation checklist (span attributes, duplicate-instrumentor check, key-leak check) and error-recovery feedback loops (401 -> other region; export errors on stderr). Matches the explicit-validation anchor; not 4 since checkpoints and recovery paths are comprehensive.

5 / 5

Progressive Disclosure

No bundle files exist and the skill is a single ~270-line file with clear, well-ordered sections (Step 0-7, Expected trace, Known behaviours, Do not) — good structure with nothing buried. Not 5: the sizable verification checklist and 'Known behaviours' material are inlined rather than split into one-level-deep reference files; not 3: organization is clear and consistent throughout.

4 / 5

Total

19

/

20

Passed

Description

92%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 concrete actions and outcomes in third person, gives an explicit 'Triggers on' clause with natural phrases, and occupies a clearly distinct Haystack+Maple niche. The only gap is modest synonym coverage in its trigger terms.

Suggestions

Add one or two common synonym triggers such as 'monitor my haystack agent', 'haystack telemetry', or 'haystack observability' to broaden natural-phrasing coverage.

Consider a shorter alias like 'maple for haystack' among the triggers, since users may phrase the request that way.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'installs a small Haystack tracer that adds OpenTelemetry GenAI attributes to Haystack's own spans' — and enumerates the concrete outcomes (transcript, model, tokens, cost, tool failures), matching the comprehensive-coverage anchor. Not 4: the action and outcome coverage has no minor gaps.

5 / 5

Completeness

Explicitly answers both what (installs a tracer adding OTel GenAI attributes so each conversation is one Maple Agent Session) and when (an explicit 'Triggers on ...' clause with concrete phrases). Not 4: the when-clause is explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Natural, user-sayable trigger phrases are present ('trace my haystack agent', 'add Maple to haystack', 'agent sessions for haystack', 'OpenTelemetry for haystack'). Not 5: common synonyms such as 'monitor', 'telemetry', or 'observability' for Haystack are missing; not 3: several natural phrases appear, not just generic keywords.

4 / 5

Distinctiveness Conflict Risk

Names both the target framework (Haystack) and the tool (Maple) with framework-specific triggers, giving it a clear niche with minimal conflict risk against generic tracing or PDF/document skills. Not 4: the double naming leaves no overlap with closely related skills.

5 / 5

Total

19

/

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

MapleTechLabs/maple

Path

skills/maple-agent-tracing-haystack/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.