CtrlK
BlogDocsLog inGet started
Tessl Logo

social-intents

Social Intents integration. Manage Organizations. Use when the user wants to interact with Social Intents data.

54

Quality

61%

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 ./skills/social-intents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 content is actionable and well-structured, led by concrete executable CLI commands and a clear connection state-machine. Its main weaknesses are marketing-flavored padding and a workflow whose step numbering is inconsistent and references a missing 'Step 2'.

Suggestions

Fix the broken workflow numbering: either add an explicit 'Step 1' / 'Step 2' labeling or replace the 'skip to Step 2' reference and the lone '1b' heading with consistent sequential headings.

Trim marketing prose such as 'so you can focus on the integration logic rather than auth plumbing' and 'This is the fastest way to get a connection' to improve token efficiency.

Populate the 'Popular actions' section with a few concrete named Social Intents actions instead of only redirecting to `action list`.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands, but includes unnecessary marketing prose such as "so you can focus on the integration logic rather than auth plumbing" and "This is the fastest way to get a connection," matching the 'mostly efficient but could be tightened' anchor. It is above a 2 because the bulk is command-driven, but below a 4 due to these padded explanatory sentences.

3 / 5

Actionability

The guide provides concrete, executable commands (login, connection ensure, action list/run, request) plus a complete proxy flags table, fitting the 'mostly executable guidance with minor gaps' anchor. It is not a 5 because the "Popular actions" section only redirects to `action list` without showing any actual named actions.

4 / 5

Workflow Clarity

The connection workflow has a clear state-machine (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) with polling, but it references a non-existent "Step 2" and labels a subsection "1b" with no corresponding "1a" or "Step 1", leaving the sequence with broken checkpoints. This fits the anchor for steps present but with missing/implicit checkpoints, and is not a 4 because the cross-references do not resolve.

3 / 5

Progressive Disclosure

As a single-file skill with no bundle files, the content is organized into clearly labeled sections (Overview, Authentication, Connecting, Searching, Proxy, Best practices) with no nested references, matching the 'good structure; most content appropriately placed' anchor. It is not a 5 because some material (e.g., the proxy flags table, agent-type list) could be split out, but the organization is solid.

4 / 5

Total

14

/

20

Passed

Description

62%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 correctly includes an explicit 'Use when' trigger and names the specific platform, giving it decent distinctiveness and completeness. Its weakness is a thin, generic 'what' that only mentions Organizations despite the body covering many more entities.

Suggestions

Expand the 'what' clause to list the concrete capabilities the skill actually exposes (e.g., 'Manage chat messages, transcripts, agents, integrations, and settings') instead of only 'Manage Organizations'.

Add natural trigger phrases users would say, such as 'live chat', 'chat transcripts', or 'social media marketing', to broaden keyword coverage beyond the platform name.

Tighten 'Social Intents integration.' into the action clause to remove the generic filler.

DimensionReasoningScore

Specificity

The description names the domain ("Social Intents integration") and one concrete action ("Manage Organizations"), matching the anchor for naming a domain with 1-2 concrete actions that are not comprehensive. It is above a 2 because it does specify a concrete action, but below a 4 because it only lists one action and omits the other entities (Chat, Transcript, Agent, etc.) shown in the body.

3 / 5

Completeness

Both the 'what' ("Manage Organizations") and an explicit 'when' ("Use when the user wants to interact with Social Intents data") are present, matching the anchor for having both with a 'when' that could be more specific. It is not a 3 because the 'when' is explicit rather than weakly implied, and not a 5 because the 'what' is generic ("integration") and covers only one entity.

4 / 5

Trigger Term Quality

Relevant keywords ("Social Intents", "Organizations", "interact with Social Intents data") are present but common variations or synonyms are missing, fitting the anchor for some relevant keywords without full coverage. It is not a 4 because the natural-term coverage is thin beyond the platform name itself.

3 / 5

Distinctiveness Conflict Risk

Naming the specific platform "Social Intents" creates a clear niche with minimal conflict risk, matching the 'mostly distinct; minor overlap risk' anchor. It is not a 5 because the generic "Manage Organizations" phrasing could overlap with other organization-management skills.

4 / 5

Total

14

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
membranedev/application-skills
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.