best-skill-recommendations

Based on user goals, comprehensively evaluate candidate skill capabilities and conflict risks with installed skills, then deliver the best install recommenda...

Security Scan

The skill's requests and runtime instructions are consistent with its stated purpose: it only uses the clawhub CLI to discover and (with explicit user confirmation) install or uninstall skills, and it asks for no extra credentials or system access.

Purpose & Capability

Name/description promise (evaluate and recommend skills, detect conflicts, and perform installs) aligns with the declared requirements: the skill needs the clawhub CLI and uses clawhub commands (search, list, install, uninstall). There are no unrelated credential or binary requests.

Instruction Scope

SKILL.md instructions are narrowly scoped: they parse upstream candidates if available, otherwise run `clawhub search`, enumerate installed skills via `clawhub list`, and only run `clawhub install`/`uninstall` after explicit pre-install confirmation. The instructions do not direct the agent to read unrelated files, environment variables, or to send data to arbitrary external endpoints.

Install Mechanism

No install spec or bundled code — this is instruction-only and relies on an existing `clawhub` binary. That is the lowest-risk install posture for this kind of skill.

Credentials

No environment variables, secrets, or config paths are requested by the skill. The only external dependency is the user-authenticated `clawhub` CLI, which stores its own credentials; the skill itself does not request or require additional credentials.

Persistence & Privilege

The skill does not request always:true, does not modify other skills' configurations, and only performs install/uninstall actions after explicit user confirmation. Autonomous invocation is allowed (platform default) but is not combined with elevated privileges or broad credential access.

Assessment

This skill appears coherent and limited to managing skills via the clawhub CLI. Before using it: ensure you trust the clawhub CLI and are logged in with the intended account; review any pre-install risk disclosures the skill presents (source, install counts, last update, author info); and confirm each install/uninstall when prompted. If you do not have or do not trust the clawhub CLI, do not run this skill.

Primary role: Evaluate and recommend skills already discovered by an upstream skill search. Only when no upstream results exist does this skill independently search clawhub, then apply the same evaluation logic.

Prerequisites

Before this skill can operate, confirm the following:

• clawhub CLI is installed and available in the agent's PATH. This skill issues clawhub search, clawhub list, clawhub install, and clawhub uninstall commands. If the binary is absent, all discovery and install steps will fail.
• Authentication: Run clawhub login in advance. The clawhub CLI stores credentials in its own default config path (managed by the CLI, not by this skill). No additional environment variables are required by this skill.
• Permissions in scope: This skill will only:
  1. Read the installed skill list via clawhub list (read-only).
  2. Run clawhub install <skill> or clawhub uninstall <skill> — only after explicit user confirmation at the Pre-Install Gate (Step 5). It will not access other system files, credentials, or APIs beyond the clawhub CLI.

Mandatory Store Policy

1. Prefer upstream results first. If any upstream skill search has already returned candidates, use those directly — do not re-search.
2. Only when no upstream candidates exist: search clawhub directly.
3. Never claim exclusivity; both public and private registries are valid.
4. Before install, always summarize source, version, and notable risk signals.
5. If a fresh search is needed, run clawhub search <keywords> and report output before evaluating.

Auto-Trigger and Collaboration

• Preferred entry: triggered after an upstream skill search has already produced a candidate list. Reuse those results directly.
• Standalone entry: triggered when the user asks to recommend/install/compare skills but no upstream results exist. In this case, independently search clawhub and produce candidates before evaluating.
• Never re-search if usable upstream candidates are already available.

Workflow

0) Check for Upstream Candidates (first)

Before doing anything else:

• If an upstream skill search has already returned a candidate list → skip to Step 2 using those results.
• If no upstream candidates exist → proceed to Step 1.

1) Self-Discover (only when no upstream results)

Clarify the user's need:

• target task(s)
• priority (speed/stability/features/safety)
• constraints (region, cost, runtime)

Then search via clawhub:

clawhub search <keywords>

Return the command output and build a candidate list annotated with source and version.

2) Evaluate Candidates

Present the candidate list (from upstream or self-discovered), annotated with source and version.

3) Evaluate Installed Skills and Compatibility

Enumerate installed skills by running:

clawhub list

Parse the output to get the current installed skill set. Compare each installed skill against candidates:

• overlap: full / partial / complementary
• conflict risk: command/workflow collision, duplicated automation, behavior mismatch
• coexist feasibility: high / medium / low

4) Recommend Replace vs Coexist

Per candidate, output one decision:

• Replace existing skill(s)
• Coexist with boundaries
• Do not install

Include reasons and trade-offs.

5) Pre-Install Gate (required)

Before any install action, present:

• source (clawhub)
• version
• notable risk signals — check for any of the following:
  • install count < 10 (low adoption)
  • last update > 6 months ago (low maintenance signal)
  • requires broad file system or network permissions
  • published < 2 weeks ago (very new, unvetted)
  • no author URL or verified identity
• replace/coexist plan

Then explicitly ask for user confirmation.

6) Install Execution

• clawhub install <skill>
• If replace approved: uninstall old first, then install new.
• If coexist: install and provide usage boundary guidance.

7) Post-Install Report

Return:

• install/uninstall result
• final active skill set
• why this is best for the user goal
• follow-up checks

Output Format

Candidate Summary

• Name
• Purpose
• Source
• Version
• Install Count (if available)
• Link

Decision Summary

• Best choice (Top 1)
• Alternatives (Top 2/3)
• Replace/Coexist decision
• Why not other options

Pre-Install Confirmation

"Planned action: <install/replace/coexist>. Source: clawhub. Version: <...>. Risks: <...>. Proceed?"

Guardrails

• Never install without explicit confirmation.
• Prefer fewer, higher-confidence recommendations over long noisy lists.
• If search quality is poor, refine keywords and re-run search before recommending.