CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

maple-agent-tracing-dspy

Trace DSPy programs and ReAct agents with Maple: OpenInference DSPy instrumentor with GenAI dual-write, a DSPy callback for tokens, cost, tool names and agent spans, using_session for one session per conversation, and thread context for dspy.Parallel. Triggers on 'trace my dspy agent', 'add Maple to dspy', 'agent sessions for dspy', 'OpenTelemetry for dspy'.

72

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 exceptionally actionable, well-sequenced setup procedure with real validation checkpoints and no padding. Its weaknesses are the monolithic single-file layout — no progressive disclosure of troubleshooting material via references — and inline version-pinned compatibility notes.

Suggestions

Move the "Known behaviours" bullets (and optionally the full maple_dspy.py callback source) into references/known-behaviours.md, linked from a short summary in the body, so the always-loaded SKILL.md carries only the Steps 0–7 core workflow.

Place the version-compatibility guidance (dspy>=3.4 requirement, the 3.3-or-older handling, the 0.66b0 threading pin) in a dedicated compatibility section or reference file so the main workflow is not tied to volatile version numbers.

Consider moving the Step 7 verification checklist details into a references/verify.md, keeping a short assertion list inline, to further reduce the token footprint of the main body.

DimensionReasoningScore

Conciseness

The body is dense and imperative throughout — it never explains concepts Claude already knows (what a span or LM is) and every step carries Maple-specific knowledge. It stays a 4 rather than a 5 because of inline volatile version pins ("dspy>=3.4", "0.66b0", "this skill targets 3.4") and a long "Known behaviours" section that a leaner split would trim.

4 / 5

Actionability

Fully executable guidance: complete copy-paste-ready files (tracing.py, maple_dspy.py given in full), exact pip install and environment variable blocks, and exact log/error strings ("OTEL_EXPORTER_OTLP_HEADERS (Maple ingest key) is not set...", "ingest_unauthorized").

5 / 5

Workflow Clarity

Steps 0–7 are clearly sequenced with pre-flight detection of existing setup (Step 0), per-step specifics, and a full verification checklist (Step 7) with error recovery feedback loops — e.g. a 401 key error routes to trying the other region's endpoint, and a local ConsoleSpanExporter fallback verifies spans without Maple access.

5 / 5

Progressive Disclosure

There are no bundle files at all; everything lives inline in one ~250-line SKILL.md. The structure is well-sectioned, but the "Known behaviours" troubleshooting list and streaming edge-case details are on-demand lookup content that belongs in a reference file, keeping the core Steps 0–7 leaner in the always-loaded body.

3 / 5

Total

17

/

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: specific, complete, and distinct, with explicit trigger guidance in natural user language. The only gap is modest synonym coverage in the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities: "OpenInference DSPy instrumentor with GenAI dual-write", "a DSPy callback for tokens, cost, tool names and agent spans", "using_session for one session per conversation", and "thread context for dspy.Parallel" — comprehensive and specific with no vague filler.

5 / 5

Completeness

Both "what" (five named capabilities) and "when" (an explicit "Triggers on ..." clause with four concrete phrases) are clearly and explicitly answered, matching the anchor-5 pattern.

5 / 5

Trigger Term Quality

Explicit trigger phrases ("trace my dspy agent", "add Maple to dspy", "agent sessions for dspy", "OpenTelemetry for dspy") are natural user phrasings, but common synonyms like "dspy telemetry", "dspy observability", or "monitor my dspy agent" are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The tightly scoped Maple × DSPy pairing with framework-specific trigger phrases creates a clear niche with minimal risk of triggering for any other skill.

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-dspy/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.