CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hindsight-docs

Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/hindsight-docs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 body is an effective, token-efficient index for a large documentation bundle: concrete glob/grep/Read guidance, a clear starting point, and one-level references that map accurately to the real file structure. Its only flaws are mild redundancy, an alternatives-not-sequence presentation of lookup methods, and a structure tree that under-reports a few bundle directories.

DimensionReasoningScore

Conciseness

The body is a lean navigation index: one-line definitions of Hindsight-specific terms only (no explanations of concepts Claude already knows), compact bullet lists, and search-pattern blocks. Minor trims exist — best-practices.md is referenced three times (tree, dedicated section, structure comment) and the 'When to Use' list duplicates the description — so it sits at anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Guidance is fully executable and copy-paste ready: exact glob patterns ('references/developer/api/*.md', 'references/**/*python*.md'), concrete grep patterns with field syntax ('pattern: "HINDSIGHT_API_"', 'pattern: "POST /v1"' with 'path: references/developer/api/'), and exact Read paths. Specific examples cover the common lookup cases, matching anchor 5.

5 / 5

Workflow Clarity

A clear lookup process is presented (find by glob, search by grep, read full docs) with an explicit entry point ('Before reading API docs, read the best practices guide'). As a read-only documentation skill it needs no validation checkpoints, but the three methods are presented as parallel alternatives rather than a sequenced decision flow, keeping it at anchor 4.

4 / 5

Progressive Disclosure

References are one level deep, clearly signaled via the directory tree, and verified against the actual bundle (best-practices.md, developer/api/retain.md, sdks/python.md, sdks/integrations/litellm.md, openapi.json, changelog/ all exist). Minor gaps: the documented tree omits the existing cloud-enterprise/ directory and several SDK files (go.md, hindsight-all*.md), so it matches anchor 4's 'minor organization gaps' rather than anchor 5.

4 / 5

Total

17

/

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 solid product-specific description that clearly states what the skill contains and includes an explicit 'Use this to' trigger clause tied to the distinctive 'Hindsight' name. Its weaknesses are the absence of concrete action verbs and of natural memory-domain trigger synonyms (memory banks, retain/recall) that users would likely say.

Suggestions

Replace the passive 'Use this to learn about' framing with concrete capability verbs, e.g. 'Look up Hindsight endpoints, configuration options, and SDK usage for retain/recall/reflect operations'.

Add natural trigger synonyms users would say, such as 'memory banks', 'memory system', 'retain/recall', or 'Hindsight SDK', so the skill fires when users phrase requests in memory-domain terms.

Make the 'when' clause user-utterance oriented, e.g. 'Use when the user mentions Hindsight, memory banks, or retain/recall operations', to reach anchor-level explicit trigger phrases.

DimensionReasoningScore

Specificity

"Complete Hindsight documentation for AI agents" names the domain and enumerates topic areas ("architecture, APIs, configuration, and best practices"), but the only action offered is the generic "Use this to learn about" — no concrete capability verbs. This matches anchor 3 (domain named, coverage not action-based), falling short of anchor 4 which expects several specific actions.

3 / 5

Completeness

The description answers both: what ("Complete Hindsight documentation for AI agents") and when ("Use this to learn about Hindsight architecture, APIs, configuration, and best practices") — an explicit trigger clause, so the missing-trigger cap of 3 does not apply. It falls short of anchor 5 because the 'when' clause lists topic categories rather than concrete user-utterance trigger phrases like 'when the user mentions Hindsight or memory retrieval'.

4 / 5

Trigger Term Quality

"Hindsight" is the dominant natural trigger and doc-category keywords ("APIs", "configuration", "best practices") are present, but common memory-domain synonyms a user would actually say — "memory banks", "retain/recall", "memory system", "SDKs" — are absent. Anchor 3 (relevant keywords missing common variations) is the best fit; anchor 4 requires only a few natural terms missing, whereas whole synonym families are missing.

3 / 5

Distinctiveness Conflict Risk

"Hindsight" is a distinctive product name creating a clear niche, and "for AI agents" scopes the audience; no realistic overlap with other skills' triggers. Matches anchor 5 (clear niche with distinct triggers, minimal conflict risk).

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: 6 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

vectorize-io/hindsight

Path

skills/hindsight-docs/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.