CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

log-watch

Set up a scheduled agent that reads a small team's existing production logs, flags suspicious activity, and pages a human, without a SIEM or security staff. Use when the user mentions 'log watch,' 'watch my logs,' 'alert me if someone is attacking,' 'no SIEM,' 'poor man's SIEM,' 'agent reads CloudTrail,' 'cron job that checks logs,' 'page me on suspicious logins,' 'Vercel logs alerting,' 'Sentry security alerts,' 'Supabase auth logs,' 'Stripe dispute spike,' 'credential stuffing alert,' 'two-stage classifier,' 'Haiku then Sonnet,' 'log monitoring cost,' or has Vercel / Heroku / Render / Sentry / Postgres / Stripe / Cloudflare / CloudTrail / GitHub logs and wants to know when something bad happens.

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 well-executed operational skill: the body is a dense, executable runbook with exact commands, thresholds, state schemas, and a validated workflow (shadow mode, heartbeat, deterministic floor, injection defenses), and detailed material is correctly split into two real, well-signaled reference files. The only notable weakness is time-sensitive pricing and model-version specifics embedded in the main body rather than isolated where staleness would be contained.

Suggestions

Move the dated pricing table and model-version specifics out of the main body into a dedicated reference (e.g. references/costs.md) or a clearly marked verify-before-quoting section, keeping only the token-cost formulas and one worked example inline so the body doesn't silently go stale.

Replace the hard-coded 'as of October 2026' prices with the recompute formulas plus a pointer to the Anthropic pricing page, presenting the current numbers as an illustrative example rather than reference data.

DimensionReasoningScore

Conciseness

The body is dense and operational — tables of exact commands, thresholds, and gotchas with no explanations of concepts Claude already knows ('Failed logins are often *not* in the table — check what's actually recorded'). However, the cost section embeds dated, version-specific figures ('first-party Claude API list prices as of October 2026 — Haiku 5.5 $0.10 / $0.50, Sonnet 5.5 $2 / $10') outside any deprecated/old-patterns section, which the guidelines penalize; the 'Re-check the Anthropic pricing page before quoting' note and recompute formulas partially self-mitigate, keeping this at anchor 4 (efficient, minor trimming/penalty) rather than 3 (nothing here is padded).

4 / 5

Actionability

Fully executable throughout: exact read commands ('aws cloudtrail lookup-events', 'gh api -X GET /orgs/ORG/audit-log', 'heroku logs -a APP --dyno router'), exact thresholds ('≥20 failures from one IP in 10 min', 'any 200 on /.env or /.git/config is critical'), a concrete state JSON schema, a paging-message template, cost formulas, and a complete single-file runner scaffold one link away in references/scaffold.md.

5 / 5

Workflow Clarity

Seven clearly sequenced steps (inventory → detections → pipeline → schedule/state → paging → untrusted input → hand-offs) with explicit validation and recovery loops: 'Run every detection in shadow mode for 7–14 days... then tune against what actually fired', the D0 heartbeat ('A silent watcher looks exactly like a quiet week'), malformed model output treated as 'stage 2 unavailable' so the deterministic alert still fires, and an untrusted-input checklist marked done/todo in the output template. The detection-only, no-write design removes the destructive-operation risk the cap targets.

5 / 5

Progressive Disclosure

The SKILL.md body is a genuine overview (summary tables for sources, detections, runners, severities), with both referenced bundle files present and real (references/detections.md with per-source queries, references/scaffold.md with the job scaffold), each clearly signaled exactly at point of need ('Queries, schemas, and discovery steps per source are in [references/detections.md]') and one level deep — the reference files contain no further nested references.

5 / 5

Total

19

/

20

Passed

Description

100%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 is a model example: third-person, concrete multi-action 'what', an unusually rich and natural 'use when' trigger list, and a sharply delineated niche (small teams, no SIEM, no security staff). No fluff, no over-claims, and no conflict risk with adjacent security skills.

DimensionReasoningScore

Specificity

'Set up a scheduled agent that reads a small team's existing production logs, flags suspicious activity, and pages a human, without a SIEM or security staff' lists multiple concrete actions covering the full pipeline (read → flag → page) with precise scope qualifiers. This matches anchor 5's comprehensive multi-action coverage; it is not anchor 4, which reserves a gap in coverage — the when-clause's triggers ('credential stuffing alert', 'Stripe dispute spike') close the remaining ground.

5 / 5

Completeness

Both halves are explicit: the 'what' ('Set up a scheduled agent that reads... flags suspicious activity, and pages a human, without a SIEM or security staff') and a concrete 'when' clause ('Use when the user mentions [15 trigger phrases] or has [platforms] and wants to know when something bad happens'). This mirrors the anchor-5 example structure exactly; not anchor 4, since the when-clause is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

The trigger list is comprehensive and phrased the way users actually talk: 'log watch,' 'watch my logs,' 'no SIEM,' 'poor man's SIEM,' 'page me on suspicious logins,' 'cron job that checks logs,' 'Stripe dispute spike,' 'Haiku then Sonnet,' plus a full platform list (Vercel / Heroku / Render / Sentry / Postgres / Stripe / Cloudflare / CloudTrail / GitHub). Natural phrasing, synonyms, and product names are all covered — anchor 5.

5 / 5

Distinctiveness Conflict Risk

'without a SIEM or security staff' carves out a clear niche with distinct triggers ('no SIEM,' 'poor man's SIEM,' platform-specific phrases like 'Vercel logs alerting'), making confusion with general SIEM, triage, or audit skills unlikely. Anchor 5: clear niche, distinct triggers, minimal conflict risk.

5 / 5

Total

20

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

briiirussell/cybersecurity-skills

Path

skills/log-watch/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.