CtrlK
BlogDocsLog inGet started
Tessl Logo

add-emacs

Add Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs (Doom, Spacemacs, or vanilla). Uses a local HTTP bridge — no bot token or external service needed.

64

Quality

81%

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

88%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.

A strongly actionable, well-sequenced setup skill with explicit validation checkpoints and thorough troubleshooting. Its only real weaknesses are mild redundancy (repeated merge-conflict instructions) and a single-file monolith structure where a couple of sections could be offloaded to references.

Suggestions

Deduplicate the merge-conflict guidance — the package-lock.json-specific instructions and the general 'read the conflicted file and reconcile both sides' paragraph (lines 54-63 and 71) cover the same ground twice.

Consider moving the per-distribution Emacs configuration blocks into a reference file (e.g. references/emacs-configs.md) so SKILL.md stays a lean overview of the workflow.

Trim or compress the 'What you can do with this' bullet list, which reads as promotional material rather than instructions the executing agent needs.

DimensionReasoningScore

Conciseness

The body is dominated by executable commands and configuration snippets with almost no explanation of concepts Claude already knows. It falls short of lean perfection mainly due to duplicated merge-conflict guidance (lines 54-63 and line 71 both cover resolving merge conflicts) and a somewhat promotional 'What you can do with this' section.

4 / 5

Actionability

Fully copy-paste-ready: exact bash commands for every phase, complete elisp blocks for all three Emacs distributions, curl verification with expected output '{"messages":[]}', and concrete troubleshooting commands including sqlite queries and lsof/kill. The common cases are covered specifically.

5 / 5

Workflow Clarity

A clear four-phase sequence with explicit validation gates: a pre-flight already-applied check, 'Build must be clean and tests must pass before proceeding' after applying changes, an expected-output curl check in Phase 4, and log-based diagnostics with feedback loops for error recovery (EADDRINUSE, 401, el not loading).

5 / 5

Progressive Disclosure

The skill has no bundle files and is well organized with clear section headers, making navigation easy. However, at ~290 lines, content such as the Removal checklist, Agent Formatting table, and the three per-distribution elisp configs could plausibly live in one-level-deep reference files, leaving minor organization gaps relative to a fully split structure.

4 / 5

Total

18

/

20

Passed

Description

65%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 distinct, concrete description whose main weaknesses are the missing 'Use when...' trigger guidance and a second-person voice penalty on specificity. Adding an explicit trigger clause and rephrasing to third person would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to chat with or send org-mode content to NanoClaw from inside Emacs (Doom, Spacemacs, or vanilla)'.

Rewrite 'so you can talk to NanoClaw from within Emacs' in third person, e.g. 'Lets the user talk to NanoClaw from within Emacs', to avoid the second-person specificity penalty.

Consider mentioning 'Emacs Lisp' / 'nanoclaw.el' as additional natural keywords users may say.

DimensionReasoningScore

Specificity

Concrete actions are named ('Add Emacs as a channel', 'Opens an interactive chat buffer', 'org-mode integration') that would anchor at 4, but the second-person phrase 'so you can talk to NanoClaw from within Emacs' incurs the rubric's 1-point voice penalty, dropping it to the '1-2 concrete actions, not comprehensive' level.

3 / 5

Completeness

The 'what' is clear and specific, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the rubric explicitly caps this at 3. It does not reach 4 because 'when to use' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Good natural keyword coverage: 'Emacs', 'chat buffer', 'org-mode', 'NanoClaw', and distribution variants 'Doom, Spacemacs, or vanilla'. A few natural terms users might say (e.g. 'Elisp', 'talk to my agent from Emacs') are missing, so it sits just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The description names a highly specific niche (adding an Emacs channel to NanoClaw via a local HTTP bridge) with distinct triggers like 'Emacs' and 'NanoClaw'; virtually no other skill would match this phrasing.

5 / 5

Total

15

/

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
jbaruch/nanoclaw-telegram
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.