build-sequence

Use when designing a finite evidence-backed outreach sequence for an eligible contact without scheduling or sending it.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/build-sequence/SKILL.md

Quality

Content

81%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 a tight, compliance-oriented instruction skill with strong gating and validation throughout. Its main weakness is the lack of a concrete worked example showing the full output structure, which would push actionability and progressive disclosure higher.

Suggestions

Add a short fully-worked example output (drafting-gate status, touch table with one or two rows, evidence ledger, terminal rules) so Claude can pattern-match the exact format.

De-duplicate the stop-condition statements between Workflow step 6 and Guardrails by cross-referencing once instead of restating.

Consider moving a worked example into a references/ file and linking it, improving progressive disclosure for this multi-step skill.

Dimension	Reasoning	Score
Conciseness	Lean, well-sectioned, and assumes Claude's competence with no padding or explanation of known concepts, but stop-condition language recurs across Workflow step 6, Guardrails, Quality check, and Output format, so it is not perfectly trimmed.	4 / 5
Actionability	Highly concrete instruction guidance with explicit return tokens (STOP, NEEDS VERIFICATION, NOT READY TO SEND), per-touch field specs, and the DRAFT FOR HUMAN REVIEW label; the only gap is the absence of a fully worked output example beyond the brief Example invocation.	4 / 5
Workflow Clarity	A clearly numbered 7-step sequence with explicit validation checkpoints (drafting gates, pre-touch rechecks, terminal stop/pause rules) and a dedicated Quality check, matching the 'clear sequence with explicit validation and feedback loops' anchor.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no unnecessary external references, but a moderately complex multi-touch skill could benefit from a separate worked-example reference rather than a one-line invocation, so it is not at the ideal split-content anchor.	4 / 5
	Total	17 / 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 is third-person, clearly scoped, and includes an explicit 'Use when' trigger alongside a concrete 'what'. It is solid but not exemplary: trigger coverage relies on a single phrase and capability breadth is narrow.

Suggestions

Add 1-2 more concrete capabilities (e.g., 'define touch timing, channels, and stop conditions') to lift specificity toward comprehensive coverage.

Broaden the trigger clause with natural synonyms a user would say, e.g., 'Use when building or planning an outreach cadence, touch plan, or follow-up sequence for an eligible contact'.

Add a brief negative trigger to reduce conflict risk, e.g., 'Do not use for scheduling, sending, or automating outreach'.

Dimension	Reasoning	Score
Specificity	Names the domain ('outreach sequence for an eligible contact') and one concrete action ('designing a finite evidence-backed outreach sequence'), but does not enumerate multiple distinct capabilities, so it sits at the 'domain + 1-2 actions' anchor rather than comprehensive coverage.	3 / 5
Completeness	Explicitly answers both what ('designing a finite evidence-backed outreach sequence... without scheduling or sending it') and when ('Use when designing...'), but the 'when' clause reuses the same phrasing rather than listing distinct trigger scenarios, keeping it just below the fully comprehensive anchor.	4 / 5
Trigger Term Quality	Contains a relevant natural phrase ('designing... outreach sequence') but lacks common synonyms, variants, or file/format triggers a user might say, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche is specific (evidence-backed outreach sequence for an eligible contact with explicit no-send constraint), giving it a clear identity with only minor overlap risk against adjacent outreach/messaging skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: llaskin/AI-SDR-Skill-Pack
Path: skills/build-sequence/SKILL.md
Commit: 56ebfd3

Reviewed: ~24 hours ago

Table of Contents

Discovery Implementation Validation

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.